From 08f1c7ad0955b5651365684c254de984aabd4c0a Mon Sep 17 00:00:00 2001 From: Frank Date: Sun, 20 Sep 2026 19:35:56 -0700 Subject: [PATCH] feat(monitoring,harness): follow frank-medium onto vllm:* metrics and fix red-by-construction targets The radiance TP=2 cutover changed the metric namespace frank-medium exports (llamacpp:* -> vllm:*) and left two scrape targets addressing host processes by an address a container cannot reach. - shared/prometheus/rules/llm-fleet.yml: two namespaces side by side. Added LlmRequestsWaiting, LlmKvCacheSaturated (vllm-only gauges llama.cpp never had), the job:llm_vllm_prefix_cache_reuse:rate5m and job:llm_spec_accept_length:rate5m recording rules, and re-cut LlmPrefixCacheCollapse / LlmSpecDecodeOff to OR both families with per-family traffic floors so an idle endpoint cannot fire them. Every expression validated against live Prometheus. - shared/prometheus/prometheus.yml: frank-small -> host.containers.internal:7771 and frank-large scraped at host.containers.internal:7770. Both are HOST processes on Dankclaw and netavark DNATs published container ports only, so the LAN-IP targets were red by construction; frank-large's CIRU llama.cpp build does export the llamacpp:* family, contra the old comment. - tests/observability_quadlet.bats: the two seams now encode the new contract (per-endpoint reachability by process type; every named series must be on the measured list for its engine; engine-independent rules must name both). - homepage docs.html/services.json: frank-medium sees pictures, frank-large is CIRU Orca with a single seat (was halogen w4b, two seats, 200k). - docs: radiance runbook is ACTIVE (deployed flags, three-arm battery, verified capabilities, rollback, replica-era sections labelled); llama.cpp runbook carries the SUPERSEDED banner; Dual-R9700-Cooperation states the measured verdict; Observability records the namespace split and the DNAT lesson; AGENTS.md topology/frank-medium/Model Config/Benchmarking Policy/runbook index flipped; both indexes updated; work-log entry added. Also repaired agent-pass damage: prose prepended above frontmatter openers, duplicated runbook bodies, a literal tool-call token pasted into a runbook, and an index destroyed by diff artifacts (restored from HEAD, flips re-applied). Vault link check: 128 pages, 0 unresolved. ./tests/run.sh: 325 pass. --- AGENTS.md | 141 +++++++------- .../Infrastructure/Observability.md | 36 ++-- .../LLM/Dual-R9700-Cooperation.md | 85 +++++--- .../LLM/frank-medium-llamacpp-dflash2.md | 19 +- .../LLM/frank-medium-radiance-mxfp4.md | 182 ++++++++++++++---- serverAppConfigs-docs/LLM/index.md | 55 +++--- serverAppConfigs-docs/index.md | 36 ++-- serverAppConfigs-docs/log.md | 143 ++++++++++++++ shared/homepage/docs.html | 10 +- shared/homepage/services.json | 2 +- shared/prometheus/prometheus.yml | 55 ++++-- shared/prometheus/rules/llm-fleet.yml | 138 +++++++++---- tests/observability_quadlet.bats | 71 ++++--- 13 files changed, 687 insertions(+), 286 deletions(-) diff --git a/AGENTS.md b/AGENTS.md index 7981930..eeb2ab5 100644 --- a/AGENTS.md +++ b/AGENTS.md @@ -24,9 +24,9 @@ merge absorbed the former `vllmScripts` repo, history preserved). | Target | Service | Runtime | Model | Port | |--------|---------|---------|-------|------| -|Dankserver|`frank-medium`|mainline llama.cpp master fb27a525 (root systemd unit, gfx1201 HIP build)|orcarouter Qwen3.8-27B-Uncensored Q8_0 with the z-lab DFlash2 Q4_K_M drafter (the model's own MTP head stays in the file, one SPEC_TYPE change away), 2x Radeon AI PRO R9700 in ONE layer-split process (32:33 balanced; both cards on CPU root ports at Gen5 x8 since the 2026-09-20 ProArt B850-Creator swap — atomic routing verified on both chains), 327680 ctx over 2 slots of 163840, batch 6144x512, f16 KV + 16 GiB host-RAM prompt cache, vision (BF16 mmproj)|7770| +| Dankserver | `frank-medium` | vllm-radiance 0.9.3 (rootless Quadlet, image `localhost/radiance-vllm:0.9.3`, gfx1201) | Qwen3.8-27B-Uncensored MXFP4-awq with the z-lab DFlash2-FP8 drafter (depth 7, live mean accept length ~4.1), 2x Radeon AI PRO R9700 in ONE tensor-parallel process (TP=2 over the R4D one-shot allreduce — no RCCL collective; both cards on CPU root ports at Gen5 x8 since the 2026-09-20 ProArt B850-Creator swap), 262144 ctx over up to 8 conversations (auto-sized 943,581-token KV pool = 3.59x the window), fp8 KV, prefix caching, vision | 7770 | | Dankclaw | `frank-large` | CIRU v4.4.1 llama.cpp (QSA window hotfix, root systemd unit, gfx1151 HIP build) | jcbtc Qwen3.8-Flash-CIRU-STRIX-Orca on the gfx1151 iGPU (Strix Halo LPDDR), 262144 ctx single stream (1 slot), MTP depth 4, PLE 4096 MiB, text only | 7770 | -| Dankclaw | `frank-small` | mainline llama.cpp master 37b53fd (root systemd unit) | HauhauCS Gemma4-12B-QAT-Uncensored-Balanced Q4_K_M (BF16 mmproj + MTP assistant sidecar, `draft-mtp,ngram-mod`) on the RTX 3090, 1048576 pool / 4 slots of 262,144, q8_0 KV, the fleet's vision endpoint | 7771 | +| Dankclaw | `frank-small` | mainline llama.cpp master 37b53fd (root systemd unit) | HauhauCS Gemma4-12B-QAT-Uncensored-Balanced Q4_K_M (BF16 mmproj + MTP assistant sidecar, `draft-mtp,ngram-mod`) on the RTX 3090, 1048576 pool / 4 slots of 262,144, q8_0 KV, the fleet's fastest vision endpoint | 7771 | Retired endpoints (`frank-npu`, and every prior runtime) are in the [runbook index](#runbook-index). The full swap history lives in @@ -68,7 +68,9 @@ All edits flow through git. Never edit files on a remote machine directly. The planner maps changed paths to services; the remote runner restarts only the selected service and records its revision outside the checkout. Documentation-only changes are a no-op. LLM services are selected only by -their own files — all three by their unit/env/serve trio in `scripts/` — so +their own files — `frank-large`/`frank-small` by their unit/env/serve trio in +`scripts/`, `frank-medium` by its Quadlet unit, entrypoint and healthcheck under +`dankserver/frank-medium/` — so unrelated container changes cannot interrupt inference. Set `FRANK_SUDO_PW` for headless runs on a host without passwordless sudo; the value never enters the repo. @@ -230,8 +232,9 @@ merely wedged kernel usually still answers ARP. `sudo systemctl stop frank-large && sudo systemctl mask frank-large` - Dankclaw `frank-small` (root unit, llama.cpp on the 3090): `sudo systemctl stop frank-small && sudo systemctl mask frank-small` - - Dankserver `frank-medium` (system unit): - `sudo systemctl stop frank-medium && sudo systemctl mask frank-medium` + - Dankserver `frank-medium` (**rootless Quadlet since 2026-09-20** — the + system unit is retired, so `sudo systemctl` sees nothing): + `systemctl --user stop frank-medium && systemctl --user mask frank-medium` 2. Bench. 3. Unmask and start; verify `curl http://192.168.0.:7770/health`. @@ -259,9 +262,14 @@ When renaming a service, retiring an endpoint, or moving a model: update the provider block, model `id`, `contextWindow`, `maxTokens`, `input` in `models.yml`, then fix every `modelRoles` entry that named the old endpoint — a role pointing at a provider the file does not define fails at call time. As -of 2026-09-16 the image path is `frank-small` (`input: [text, image]`), and -`frank-large` is text-only because its CIRU deployment loads no vision -projector (the F16 mmproj is on disk, one env flip away). There is **no audio** +of 2026-09-20 both `frank-small` and `frank-medium` accept images +(`input: [text, image]`) — frank-medium's checkpoint serves vision through the +Gemma4 merge path with no separate mmproj, verified on held-out synthetic +images; `frank-large` remains text-only because its CIRU deployment loads no +vision projector (the F16 mmproj is on disk, one env flip away). Note also that +the reasoning channel differs by runtime: llama.cpp endpoints emit +`reasoning_content`, vLLM emits `reasoning`. +There is **no audio** input anywhere in the fleet: that capability left with the FLM NPU endpoint on 2026-09-11. @@ -326,63 +334,49 @@ ubatch 2048 OOMs the draft's pp buffer, and why draft depth 4 + poll Runbook: `serverAppConfigs-docs/LLM/frank-small-gemma4-12b.md`. Rollback: [[frank-small-qwen38-gsq-rco]]. -### frank-medium — llama.cpp layer split, DFlash2 drafter (Dankserver, ACTIVE) +### frank-medium — radiance TP=2, DFlash2-FP8 drafter (Dankserver, ACTIVE) -Mainline llama.cpp at **`fb27a525`** (a gfx1201 HIP build, `Root=`-less root -systemd unit `scripts/frank-medium.service`) serving -`orcarouter/Qwen3.8-27B-Uncensored-GGUF` at **Q8_0** (27.0 GiB) with the -**z-lab DFlash2 `Q4_K_M` drafter** (1.06 GiB). The target file also carries the -model's own MTP head (`blk..nextn.*`, `nextn_predict_layers=1`), so -`draft-mtp` is one `SPEC_TYPE` change away — the drafter file stays on disk. In -**one process across both R9700s**, `--split-mode layer` at a **32:33 tensor -split** — balanced (operator call 2026-09-19, the most even split 65 layers -allow; ROCm1, the last-layers card that also carries the drafter and output -layers, holds the extra one). -The predecessor's 35:30 skew (2026-09-17) leaned work onto the wider card -because ROCm1 (then `0b:00.0`) rode the B650 chipset at Gen4 x1 (~1.97 GB/s) -against ROCm0's CPU-root-port Gen4 x16 (~31.5 GB/s); the balanced point traded -that lean for symmetry and was accepted. The 2026-09-20 board swap (ASUS ProArt -B850-Creator WiFi NEO) removed the other axis: both cards are now CPU-root-port -Gen5 x8 (~31.5 GB/s each), at `03:00.0` and `07:00.0`. 327680 ctx -over **2 slots** of 163840 — inside the checkpoint's trained 262144 window, so -no rope extrapolation (unlike the predecessor's 393216) — batch 6144x512, f16 -KV, a 16384 MiB host-RAM prompt cache, vision via the BF16 mmproj. DSpark was -tried in the drafter's place on 2026-09-16 and reverted: it declares no sliding -window, so its draft KV spanned the whole context (5.0 GiB) and cost ROCm1 four -layers of the split. +vllm-radiance **0.9.3** (`localhost/radiance-vllm:0.9.3`, rootless **Quadlet** +`dankserver/frank-medium/quadlet/frank-medium.container`) serving +`just1moremodel/Qwen3.8-27B-Uncensored-MXFP4-awq` (MXFP4) with the +**z-lab DFlash2 FP8 drafter** (`num_speculative_tokens: 7`, live mean accept +~4.1) in **one tensor-parallel process across both R9700s** +(`--tensor-parallel-size 2`). 262,144 ctx, `--max-num-seqs 8`, chunk 8192, fp8 +KV, prefix caching, GPU fill 0.98, **no KV-memory pin** — the pool auto-sized +to 943,581 tokens (3.59× the full window). Tools via `qwen3_coder`, reasoning +via `qwen3` (the field is `reasoning`, not llama.cpp's `reasoning_content`), +vision through the Gemma4 merge path with `MM_MERGE_ENGINE=AXROW_SEPARATE`. -**Layer split is why both cards serve ONE model today.** It was chosen because -tensor parallelism was then impossible (see the PCIe lesson below) and so was -vLLM's pipeline parallelism — its stage handoff is an RCCL `send`/`recv` of the -hidden state, the exact primitive that could not be dispatched on the old -board's card #2. llama.cpp's layer split needs -no collective at all: layers are distributed in order and the boundary -activation is a per-backend copy, once per forward pass. Measured on this host -(the predecessor runtime): 1991 t/s prefill layer-split vs 272 tensor — but that -tensor number is the cost of a butterfly-fallback allreduce with `GGML_HIP_RCCL` -OFF, not what an RCCL-backed tensor split would do. Since the 2026-09-20 board -swap cleared the atomics gate, that comparison is stale and the probe is the -open work; see [[Dual-R9700-Cooperation]]. +**TP=2 runs because the board changed.** The predecessor board (TUF GAMING +B650-E) put card #2 behind chipset bridges advertising `AtomicOpsCap: Routing-` +and no collective could be dispatched there. The ProArt B850-Creator WiFi NEO +routes both cards to CPU GPP root ports (`00:01.1 → 03:00.0`, +`00:01.3 → 07:00.0`, Gen5 x8, every hop `Routing+`, both endpoints `ReqEn+`). +The collective in use is vLLM's **R4D one-shot allreduce**, which never touches +RCCL (TheRock RCCL has no gfx1201 device code; the Ubuntu RCCL 2.27 build does, +and that is what `scripts/build-llama-rdna4.sh GGML_HIP_RCCL=ON` links). -This is the box's **only** LLM runtime: the vllm-radiance replica pair and its -routing proxy (`frank-medium-a/-b/-proxy`) were retired the same day they went -live, with their units moved to `~/.AGENTTRASH/20260916-vllm-radiance-retire/`. +**Measured, not assumed** (`scripts/bench-conversation.py`, 10 real prompts, +max_tokens 512, greedy, salted per arm, service stopped between arms): +radiance TP=2 95.8 t/s decode geomean / 0.21 s TTFT / 259.4 t/s burst-4, vs the +llama.cpp layer split's 45.7 / 0.72 / 71.7 and llama.cpp `--split-mode tensor`'s +30.5 / 0.71 / 54.3. Honest caveat: the arms also differ in quantization (MXFP4 +vs Q8_0), so part of the margin is the quant, not the parallelism. Re-measured +against production after deploy: 92.4 t/s, 0.22 s, 248.9. -Files: `scripts/build-llama-rdna4.sh` (builds the runtime, gfx1201 only, private -ROCm 7.14 toolchain bundled beside the binary), `scripts/download-frank-medium-gguf.sh` -(resumable, byte-verified payload), `scripts/frank-medium.env`, -`scripts/serve-frank-medium.sh`, `scripts/frank-medium.service`. The deploy -handler refuses to start a unit whose runtime or payload is missing, retires -the vLLM quadlets, waits for 7770 to be released (the retired proxy held it) and -gates on `/health`. +Files: `dankserver/frank-medium/quadlet/frank-medium.container`, +`dankserver/frank-medium/radiance-entrypoint.sh`, +`dankserver/frank-medium/frank-medium-healthcheck.py`. The llama.cpp layer-split +trio (`scripts/frank-medium.service`, `.env`, `serve-frank-medium.sh`) is +archived in `scripts/.AGENTTRASH/20260920-llama-layersplit/` and is the +rollback target; `deploy-remote.sh`'s `retire_llama_medium_unit` moved the +installed unit symlink there rather than `systemctl disable`, which would delete +it. The deploy handler gates on the image tag, both model configs, the patch +clone + jinja template, and `libr4d`, then waits for :7770 and gates on +`/health`. -The ref is pinned by two features and must not float: **DFlash2** -(ggml-org/llama.cpp#27342) and **qwen35 MTP**. The ROCmFPX fork the endpoint -used earlier that day has neither. - -Runbook: `serverAppConfigs-docs/LLM/frank-medium-llamacpp-dflash2.md`. -Retired runtimes: [[frank-medium-radiance-mxfp4]] (vLLM replicas, same day), -[[frank-medium-rocmfpx]] (llama.cpp fork, earlier that day). +Runbook: `serverAppConfigs-docs/LLM/frank-medium-radiance-mxfp4.md`. +Rollback: [[frank-medium-llamacpp-dflash2]] (SUPERSEDED 2026-09-20). ## Key Lessons Learned Durable operational lessons from the fleet's history. Full detail in the @@ -412,9 +406,14 @@ linked runbooks. every bridge now `Routing+` and **both endpoints `ReqEn+`** — the exact precondition the old test plan named. Bandwidth was never the constraint (a 27B TP=2 allreduce at batch 4 is ≈10 MB per token-step, ≈1.4 ms at Gen4 x4 - and under 0.4 ms at Gen5 x8). **What is NOT yet re-measured:** no collective - has been dispatched since the swap, so TP=2 is unblocked, not proven. Full - evidence matrix and the standing probe plan: [[Dual-R9700-Cooperation]]. + and under 0.4 ms at Gen5 x8). + **Proven on the same day.** vLLM's R4D one-shot allreduce runs TP=2 here and + frank-medium serves on it; llama.cpp's RCCL path was built too + (`GGML_HIP_RCCL=ON`) and its tensor mode measured — real collective, slower + shape. Note the collective choice matters: TheRock's RCCL builds lack gfx1201 + device code (`invalid device function`), which is why R4D is the path vLLM + uses at all. Evidence matrix and the measured three-arm verdict: + [[Dual-R9700-Cooperation]]. - **When a GPU collective dies, read the runtime, not the framework.** The message that identified the cause came from `AMD_LOG_LEVEL=3` (`Pcie atomics not enabled, hostcall not supported` → `AQL dispatch @@ -428,7 +427,11 @@ linked runbooks. collective: layers are distributed in order and only the boundary activation crosses PCIe, once per forward pass. Measured here: 1991 t/s prefill / 18.8 tok/s decode layer-split, against 272 / 26.3 tensor (butterfly - fallback). That is what `frank-medium` runs — see + fallback). + This was what `frank-medium` ran until 2026-09-20, when the board swap made + collectives legal and radiance TP=2 beat it on every axis (95.8 vs 45.7 t/s + decode, 0.21 vs 0.72 s TTFT, 259 vs 72 t/s burst-4) — see + [[frank-medium-radiance-mxfp4]]; the llama shape is the rollback target [[frank-medium-llamacpp-dflash2]]. - **Layer split is also the cross-vendor answer — and `-ot` is what cannot be combined with it.** On Dankclaw (2026-09-16) a CUDA 3090 + Vulkan iGPU layer @@ -467,9 +470,10 @@ linked runbooks. **ROCm / GPU** -- **Layer split is the deployed shape on both multi-device llama.cpp services, - for two different reasons.** On Dankserver it is the *only* way both R9700s - serve one model (no collective can be dispatched on card #2). On a +- **Layer split was the deployed shape on both multi-device llama.cpp services, + for two different reasons.** On Dankserver it was the *only* way both R9700s + served one model (no collective could be dispatched on card #2) until the + 2026-09-20 board swap; frank-medium now runs radiance TP=2 instead. On a RCCL-less fork build it is also the fast one: tensor parallel falls back to a butterfly allreduce and collapses prefill ~7x (measured 271.8 vs 1991 t/s). Pin the spec-decode drafter to one device — an unpinned draft under tensor @@ -717,7 +721,7 @@ Active: |---------|---------| | frank-large (CIRU v4.4.1 Orca, Dankclaw) | `serverAppConfigs-docs/LLM/frank-large-ciru-orca.md` | | frank-small (llama.cpp Gemma4-12B QAT, Dankclaw) | `serverAppConfigs-docs/LLM/frank-small-gemma4-12b.md` | -| frank-medium (llama.cpp + MTP, Dankserver) | `serverAppConfigs-docs/LLM/frank-medium-llamacpp-dflash2.md` | +| frank-medium (radiance TP=2 + DFlash2, Dankserver) | `serverAppConfigs-docs/LLM/frank-medium-radiance-mxfp4.md` | | Dankclaw kernel posture (`amd_iommu=off`) | `serverAppConfigs-docs/LLM/dankclaw-iommu-translation-off.md` | | Deployment flow + incidents | `serverAppConfigs-docs/LLM/deployment.md` | @@ -739,6 +743,7 @@ Retired (rollback targets and history): | FreeToken (official + Huihui FP8, `frank-small`) | Dankserver | 2026-09-02 → 09-15 | `freetoken-frank-small.md` | | FastMTP patched llama.cpp | Dankserver | retired 2026-08-18 | `qwen3.8-spec-matrix.md` | | ik_llama.cpp Ornith CRACK | Dankserver | retired 2026-09-02 | `ikllama-ornith-dankserver.md` | +| llama.cpp layer split + DFlash2 (`frank-medium`) | Dankserver | 2026-09-16 → 09-20 | `frank-medium-llamacpp-dflash2.md` | Retired runbooks are under `serverAppConfigs-docs/LLM/`. Retired scripts live in `old/` and `.AGENTTRASH/`. diff --git a/serverAppConfigs-docs/Infrastructure/Observability.md b/serverAppConfigs-docs/Infrastructure/Observability.md index 9348ee8..6bc076a 100644 --- a/serverAppConfigs-docs/Infrastructure/Observability.md +++ b/serverAppConfigs-docs/Infrastructure/Observability.md @@ -41,6 +41,7 @@ Recorded 2026-09-11, on the day the stack moved to Quadlet units. Everything in - **Grafana has a datasource and one dashboard as of 2026-09-16; before that it had neither.** `shared/grafana/provisioning/` is installed to `/opt/grafana/provisioning` by the deployer and read by the container: the Prometheus datasource (`http://prometheus:9090`, fixed uid `prometheus`) and the **LLM fleet — capacity and reuse** dashboard (speculative acceptance, queue depth, prefix-cache reuse, decode step rate, throughput) covering the llama.cpp endpoints. **Re-cut on 2026-09-16**: the panels were keyed to `vllm:` series, which stopped existing when frank-medium moved to llama.cpp, and two of them (KV-pool fill, request-latency p95) have no llama.cpp equivalent at all — those two are retired rather than restated, and the acceptance panel replaces the KV one. A renamed query against a series that does not exist is a panel that draws nothing forever. Verified through the API rather than by eye — the datasource answers `llamacpp:` counters for `frank-medium`, and `GET /api/search?type=dash-db` returns uid `llm-fleet`. One trap worth knowing: a provisioned dashboard does **not** appear in the legacy `dashboard` table on this Grafana version (it lives in unified storage … - **Grafana's dashboard now also surfaces firing alerts.** The **Alerts firing (ALERTS)** panel graphs `ALERTS{alertstate="firing"}` for the LLM rules, because this stack has no other place where an alert becomes visible without opening Prometheus. - **Prometheus now evaluates rules, and they are delivered (2026-09-17).** `shared/prometheus/rules/llm-fleet.yml` ships with the config (the deployer's `copy_prometheus_config` installs both — a rule file nothing loads evaluates nothing, and Prometheus reports no error for that) and holds five rules for the LLM fleet: request queueing, prefix-cache collapse, speculative decoding off, endpoint down, plus the `job:llm_prefix_cache_reuse:rate5m` recording rule the alert and the dashboard share. **Two rules from the vLLM era were retired, not renamed**, because the series they watched no longer exist: KV-pool saturation (llama.cpp exports no KV-fill gauge; its consequence *is* queueing, which `LlmRequestsQueueing` already covers) and p95 request latency (no latency histogram). `LlmSpecDecodeOff` takes the second slot — the failure a client cannot see, since a lost drafter just halves the speed. Verified with `promtool check rules` and `/api/v1/rules` (`health=ok` for all five). **Delivery went live 2026-09-17**: the `alerting:` block in `prometheus.yml` points at `alertmanager:9093` (container name on `dankclaw_default` — the published port is loopback-only and would be wrong from inside Prometheus). Alertmanager groups by `alertname` (30 s group wait, 5 m interval, 4 h repeat) and webhooks the host-side **Signal relay** at `host.containers.internal:18093/alertmanager` — the relay binds the host's LAN IP (192.168.0.143:18093, the one address netavark delivers that dial to), with an iptables set admitting loopback, the host and the podman bridge subnet only. The relay (`scripts/signal-relay.py`, a systemd *user* unit, not a quadlet — it runs python3 from the checkout and can be enabled) dedupes per group for 15 minutes and sends through **signal-cli account 318311** (`/usr/local/bin/signal-cli`, state in `~/.local/share/signal-cli`), Frank's existing account. The Grafana dashboard's ALERTS panel and Prometheus' `/alerts` remain the second and third surfaces. +- **2026-09-20: the rule file now spans two metric namespaces.** frank-medium cut over to radiance/vLLM, so `llm-fleet.yml` carries `vllm:*` rules beside the `llamacpp:*` ones — seven alerts and two recording rules in total. KV-pool saturation and preemption pressure came back (they were retired 2026-09-16 for want of a llama.cpp gauge; vLLM exports both), and the two engine-independent rules — `LlmSpecDecodeOff`, `LlmPrefixCacheCollapse` — OR the two families and are floored on each family's own traffic counter so an idle endpoint cannot fire them. **The provisioned dashboard is the known gap:** its panels are still keyed to `llamacpp:*` series, so frank-medium's row went blank at the cutover while frank-small's and frank-large's still draw. Re-cut pending — the KV-fill and latency panels that were retired for llama.cpp have vLLM equivalents again (`vllm:kv_cache_usage_perc`, `vllm:inter_token_latency_seconds`). - **Loki is configured but unread.** Storage is filesystem with 30-day retention, `auth_enabled: false`, and the push path works; Grafana can now reach it in Explore, but no dashboard or alert consumes it. - **node-exporter runs its default collector set** — no collector tuning, no textfile collector for custom metrics. - **Alloy is the one configured piece.** It ships the host journal and podman container logs to Loki with `job` labels, and that pipeline is live. @@ -88,26 +89,31 @@ The rule is the same as for every other service: the only off-host path is a gua | `grafana`, `loki` | `grafana:3000`, `loki:3100` | container names on `dankclaw_default` | | `comfyui` | `comfyui:8188` | UI probe, no native exporter | | `services` | `192.168.0.143:8081`, `:3005` | SearXNG, OpenWebUI up/down probes | -| `frank-medium` | `192.168.0.235:7770` | llama.cpp on Dankserver — `llamacpp:` counters, including the spec-decode pair | -| `frank-small` | `192.168.0.143:7771` | llama.cpp on Dankclaw's RTX 3090 — `llamacpp:` counters, including the spec-decode pair | +| `frank-medium` | `192.168.0.235:7770` | radiance/vLLM on Dankserver — `vllm:` counters: KV fill, queue depth, preemptions, prefix-cache reuse, and the `spec_decode_*` trio | +| `frank-small` | `host.containers.internal:7771` | llama.cpp on Dankclaw's RTX 3090 — `llamacpp:` counters, including the spec-decode pair | +| `frank-large` | `host.containers.internal:7770` | CIRU llama.cpp on Dankclaw's iGPU — 19 `llamacpp:` families | The LLM endpoints were added on 2026-09-16, after a night spent diagnosing frank-medium by hand, and re-cut the same day when Dankclaw split into two -endpoints. The vLLM runtime behind that diagnosis is retired; frank-medium -now runs mainline llama.cpp, and the endpoint exports llama.cpp's own -counters — prompt and decode throughput, KV fill, and the `spec_decode_*` -pair that proves the drafter is running (draft-mtp on both endpoints as of 2026-09-17). -this hardware is in [[frank-medium-llamacpp-dflash2]]; the same counter -family on frank-small is read against [[frank-small-qwen38-gsq-rco]]. +endpoints. frank-medium has since changed runtime twice (vLLM → mainline +llama.cpp → radiance/vLLM on 2026-09-20), and the metric family it exports +changed with it: `llamacpp:*` while it ran llama.cpp, `vllm:*` now. -**`frank-large` is deliberately NOT scraped.** The halogen engine publishes -`/health`, `/cache` and `/v1/*` and no Prometheus text endpoint at all, so a -target there would be red by construction and would fire `LlmEndpointDown` -forever — the same class of defect as the page-only probes below. Its liveness -is on the homepage (a loopback probe) and in the engine's own boot ledger. +**Both Dankclaw targets are addressed as `host.containers.internal` +(169.254.1.2), never the LAN IP.** frank-large and frank-small are *host +processes* on Dankclaw, and netavark DNATs only *published* container ports — +from the Prometheus container `192.168.0.143:7770/:7771` is refused even +though it answers from every other vantage on the LAN. Both targets were red +by construction until a live `/targets` audit caught it on 2026-09-20. +`frank-medium` keeps its LAN address: it is a rootless Quadlet on another host +that publishes 7770, so its published-port DNAT does apply. -Both scraped endpoints are reached on their LAN addresses, never through the -guarded vhosts: Prometheus cannot solve an Anubis challenge. +**`frank-large` IS scraped as of 2026-09-20.** The earlier claim that it had +"no Prometheus text endpoint at all" was true of the halogen engine it ran +then; the CIRU llama.cpp build that replaced it exports the full +`llamacpp:*` family, which is what makes the target addressable at all. Its +liveness is additionally on the homepage (a loopback probe) and in the +engine's own boot ledger. For services without a native exporter, use the Prometheus **blackbox exporter** in probe mode to assert up/down and HTTP latency. The homepage status timer probes the same endpoints from the host. diff --git a/serverAppConfigs-docs/LLM/Dual-R9700-Cooperation.md b/serverAppConfigs-docs/LLM/Dual-R9700-Cooperation.md index 5ad3f19..67b67d9 100644 --- a/serverAppConfigs-docs/LLM/Dual-R9700-Cooperation.md +++ b/serverAppConfigs-docs/LLM/Dual-R9700-Cooperation.md @@ -14,12 +14,11 @@ timestamp: 2026-09-16 # Dual R9700 Cooperation -Dankserver's two R9700s serve `frank-medium` as **one llama.cpp process with a -layer split** ([[frank-medium-llamacpp-dflash2]]). This page records why true -tensor parallelism was impossible on the previous board (TUF GAMING B650-E -WIFI), and what the 2026-09-20 board swap changed. See -[[frank-medium-radiance-mxfp4]] for the replica-pair deployment that ran under -the old constraint. +Dankserver's two R9700s serve `frank-medium` as **one vLLM-radiance process at +tensor_parallel_size 2** ([[frank-medium-radiance-mxfp4]]). This page records why +true tensor parallelism was impossible on the previous board (TUF GAMING B650-E +WIFI), and what the 2026-09-20 board swap changed. The llama.cpp layer split that +served the endpoint until that swap is [[frank-medium-llamacpp-dflash2]]. ## The short answer @@ -35,18 +34,21 @@ bifurcates the CPU's GPP ports **x8/x8**: the board-swap path this page recommended, at B850 rather than X870E money. Both cards now hang off CPU root ports (`00:01.1`, `00:01.3`), every bridge on both chains reads `AtomicOpsCap: Routing+`, and **both endpoints read `AtomicOpsCtl: ReqEn+`** — -the exact precondition this page's own [test plan](#test-plan) names. +the exact precondition this page's own test plan named, and it is now +[measured](#measured-verdict-2026-09-20) rather than assumed. -What that buys, and what it does not: +What that bought: -- **Unblocked in principle:** vLLM TP=2, vLLM PP=2, and llama.cpp - `--split-mode row`. All three died on the same hostcall gate. -- **Not yet measured.** Nothing has dispatched a collective on this host since - the swap. The 2-rank probe is the remaining gate, and policy is stop-and-mask - production first. -- **Not needed for capability.** The layer split already puts both cards on one - model. This is a performance question: an RCCL-backed tensor split, and the - single pooled KV that comes with it. +- **Both cooperation modes now work, and they were both run.** vLLM TP=2 booted + and served (its R4D allreduce needs no RCCL collective at all), and llama.cpp + `--split-mode tensor` booted and served against an RCCL-backed build — so a + collective HAS been dispatched on this host since the swap. +- **One of them is production.** TP=2 wins on every axis measured, by 2.1x on + decode and 3.6x at 4-way concurrency, so it replaced the layer split on the day + of measurement. See [[frank-medium-radiance-mxfp4]] for the deployed shape. +- **The drafter, not the collective, is what llama.cpp lost.** Its tensor mode + could not carry the DFlash2 drafter, which is the honest caveat on the + comparison below. - **The bandwidth story moved too.** Both cards ride Gen5 x8 (~31.5 GB/s each): card 0 effectively unchanged (was Gen4 x16), card 1 up ~16x (was Gen4 x1, ~1.97 GB/s). The M.2→PCIe riser plan is dead — `PCIEX16_2` holds card #2 now @@ -211,28 +213,47 @@ landed, at x8/x8, clears the arithmetic with room to spare. - Independent corroboration: StillDeadcode/vllm-radiance Codeberg issue #22 — different host, same image, kernel 7.0.0-30, same `enqueue.cc` failure. -## Test plan (when the hardware changes) +## Measured verdict (2026-09-20) -**Precondition met 2026-09-20:** the line below reads `ReqEn+` on both cards, so -this is now a standing plan rather than a hypothesis. +Both cooperation modes were run on this host on 2026-09-20 — the same salted +10-prompt battery (`scripts/bench-conversation.py`), the service stopped and +masked between arms. Decode/prefill are geometric means over the ten rows; +burst-4 is four concurrent copies of one prompt, reported as aggregate tokens/s. -The verdict to look for is one line of `lspci`, before touching any model: +| Shape | Cross-device path | Decode | TTFT | Prefill | burst-4 | +|---|---|---|---|---|---| +| **radiance TP=2 + DFlash2 — deployed** | R4D one-shot allreduce | **95.8 t/s** | **0.21 s** | **1493.6 t/s** | **259.4 t/s (65.6/stream)** | +| llama.cpp layer split 32:33 + DFlash2 — predecessor | none, boundary activation copy | 45.7 t/s | 0.72 s | ~530 t/s | 71.7 t/s | +| llama.cpp `--split-mode tensor` 1:1 | RCCL allreduce | 30.5 t/s | 0.71 s | n/r | 54.3 t/s | -```bash -sudo lspci -vv -s | grep AtomicOpsCtl # want: ReqEn+ -``` +Row 3 carries a caveat that no flag can remove: llama.cpp's tensor mode could not +load the DFlash2 drafter (it aborts at `ggml-backend.cpp:941` — a draft weight +pre-allocated on the non-primary device has no backend once `n_copies == 1`), so +it decoded **without** speculation while the other two rows decoded with it. The +comparison that decides anything is row 1 against row 2, and some of that gap is +the 4-bit MXFP4 checkpoint rather than the parallelism. -If that reads `ReqEn+`, the rest is mechanical: `--tensor-parallel-size 2` with -`HIP_VISIBLE_DEVICES=0,1`, then the same benchmark set -(`scripts/bench-turn-latency.py`, and the endpoint's own `timings` block) so the -two architectures are compared on identical workloads. If it still reads -`ReqEn-`, the card is still on a non-atomic path — check `lspci -tv` for the -bridge chain rather than assuming the move worked. +Two numbers elsewhere on this page are therefore not interchangeable: + +- The 272 t/s recorded 2026-09-16 is **prefill**, on a **butterfly** allreduce, + with RCCL off, on the old board. It was never a TP decode number. +- 26.3 t/s from the same table is that butterfly tensor's decode. Row 3's 30.5 is + an RCCL tensor decode a day later: same shape family, different collective path. + +RCCL needs PCIe atomics on *every* participating GPU — the gate the old board +failed. vLLM's R4D one-shot allreduce dispatches no collective at all, which is +why TP=2 runs today rather than merely "being unblocked": the image ships TheRock +RCCL, and TheRock carries no gfx1201 device code (`invalid device function`), so +radiance could not have used RCCL on this host even with atomics routed. Ubuntu's +RCCL 2.27 does carry gfx1201 kernels, and that is what row 3 linked against. **Rule for any future multi-GPU collective experiment: stop and mask the -production service first** (`sudo systemctl stop frank-medium && sudo systemctl -mask frank-medium`, per the benchmarking policy), or run it on a host that is -not serving users. On 2026-09-16 a bare RCCL P2P probe was run against the live +production service first**, per the benchmarking policy, or run it on a host that +is not serving users. Since 2026-09-20 `frank-medium` is a rootless quadlet, so +that is `systemctl --user stop frank-medium && systemctl --user mask frank-medium` +on Dankserver. + +This is not theoretical: on 2026-09-16 a bare RCCL P2P probe was run against the live service; the host went hard down ~20 minutes later (no ARP, no ICMP, required a power cycle). The mechanism is not proven, but a hung AQL dispatch wedging the GPU driver is a plausible cause and this host has precedent for going diff --git a/serverAppConfigs-docs/LLM/frank-medium-llamacpp-dflash2.md b/serverAppConfigs-docs/LLM/frank-medium-llamacpp-dflash2.md index ea4df1d..3abaddf 100644 --- a/serverAppConfigs-docs/LLM/frank-medium-llamacpp-dflash2.md +++ b/serverAppConfigs-docs/LLM/frank-medium-llamacpp-dflash2.md @@ -1,7 +1,7 @@ --- type: configuration title: frank-medium llama.cpp Runbook (DFlash2 drafter) -description: The ACTIVE frank-medium deployment since 2026-09-16 (model swapped 2026-09-19) — mainline llama.cpp on Dankserver serving orcarouter/Qwen3.8-27B-Uncensored-GGUF at Q8_0 with the z-lab DFlash2 Q4_K_M drafter (the model's own MTP head stays in the file, one SPEC_TYPE change away), as ONE layer-split process across both Radeon AI PRO R9700 cards at a balanced 32:33 split, a 327680-position KV pool (163840 per conversation over two slots), f16 KV plus a 16 GiB host-RAM prompt cache, vision via the BF16 mmproj. +description: The former ACTIVE frank-medium deployment since 2026-09-16 (model swapped 2026-09-19) — mainline llama.cpp on Dankserver serving orcarouter/Qwen3.8-27B-Uncensored-GGUF at Q8_0 with the z-lab DFlash2 Q4_K_M drafter (the model's own MTP head stays in the file, one SPEC_TYPE change away), as ONE layer-split process across both Radeon AI PRO R9700 cards at a balanced 32:33 split, a 327680-position KV pool (163840 per conversation over two slots), f16 KV plus a 16 GiB host-RAM prompt cache, vision via the BF16 mmproj. tags: - frank-medium - dankserver @@ -12,12 +12,17 @@ tags: - gfx1201 - r9700 - layer-split -timestamp: 2026-09-19 +timestamp: 2026-09-20 --- +> **SUPERSEDED 2026-09-20.** Replaced by [[frank-medium-radiance-mxfp4]] +> (radiance TP=2, measured faster on every axis). The layer-split shape below is +> the rollback target, and the llama.cpp measurements in this page stay valid for +> it — but nothing here is the deployed shape any more. + # frank-medium — llama.cpp (DFlash2 drafter) -The ACTIVE frank-medium deployment since 2026-09-16 (model swapped to +The frank-medium deployment from 2026-09-16 to 2026-09-20 (model swapped to orcarouter Q8_0 on 2026-09-19): **mainline llama.cpp** serving `orcarouter/Qwen3.8-27B-Uncensored-GGUF` at `Q8_0` with the **z-lab DFlash2** `Q4_K_M` block-diffusion drafter, as **one process across both @@ -26,9 +31,11 @@ model (ajgazin Swift-Qwen3.8-27B UD-Q8_K_XL, 35:30 skew, 393216 pool) is the calibration history in the sizing tables below. DSpark was tried in the drafter's place on 2026-09-16 and reverted — see *The DSpark excursion*. It replaced the vllm-radiance MXFP4 replica pair + routing proxy -([[frank-medium-radiance-mxfp4]], the record and the PCIe-atomics evidence) in -the same day the pair went live. It is also the box's **only** LLM runtime: the -replicas, the proxy and their unit files are retired. +([[frank-medium-radiance-mxfp4]] holds that record, and the PCIe-atomics +evidence) the same day the pair went live — and was itself replaced by +radiance TP=2 on 2026-09-20, once the board swap made a collective legal. +During its window it was the box's **only** LLM runtime: the replicas, the +proxy and their unit files were retired. ## Why one process and layer split diff --git a/serverAppConfigs-docs/LLM/frank-medium-radiance-mxfp4.md b/serverAppConfigs-docs/LLM/frank-medium-radiance-mxfp4.md index a79e3e4..192451e 100644 --- a/serverAppConfigs-docs/LLM/frank-medium-radiance-mxfp4.md +++ b/serverAppConfigs-docs/LLM/frank-medium-radiance-mxfp4.md @@ -1,7 +1,7 @@ --- type: configuration title: frank-medium vllm-radiance MXFP4 Runbook -description: vllm-radiance MXFP4 serving just1moremodel/Qwen3.8-27B-Uncensored-MXFP4-awq as frank-medium on Dankserver (2x AMD Radeon AI PRO R9700, gfx1201), as two single-GPU replicas behind an adaptive-routing proxy — and the PCIe-atomics reason TP=2 cannot run on this host. +description: ACTIVE frank-medium runbook since 2026-09-20 — vllm-radiance MXFP4 serving just1moremodel/Qwen3.8-27B-Uncensored-MXFP4-awq as ONE tensor-parallel process (TP=2) on Dankserver's two AMD Radeon AI PRO R9700 (gfx1201), with a DFlash2-FP8 drafter. Vision is served by the loaded checkpoint (verified on synthetic images 2026-09-20). The sections below describe the 2026-09-16 two-replica era. tags: - frank-medium - dankserver @@ -13,28 +13,121 @@ tags: - rccl - pcie-atomics - quadlet -timestamp: 2026-09-16 +timestamp: 2026-09-20 --- -> **SUPERSEDED 2026-09-16.** This page is the record of the retired -> vllm-radiance MXFP4 deployment. The ACTIVE frank-medium is mainline -> llama.cpp with the DFlash2 drafter ([[frank-medium-llamacpp-dflash2]]); -> the PCIe-atomics evidence in this page remains the reason the runtime is -> layer-split llama.cpp rather than tensor-parallel vLLM. - # frank-medium vllm-radiance MXFP4 Runbook -The ACTIVE frank-medium deployment (since 2026-09-15/16): the -`stilldeadcode/vllm-radiance:0.9.3` image plus the `ggz14/radiance-vllm-mxfp4` -patches, serving `just1moremodel/Qwen3.8-27B-Uncensored-MXFP4-awq` on the two -Radeon AI PRO R9700 (gfx1201) cards. It replaced the charlie12345/ROCmFPX -llama.cpp deployment ([[frank-medium-rocmfpx]]). +The ACTIVE frank-medium deployment: the `stilldeadcode/vllm-radiance:0.9.3` +image (tagged locally as `localhost/radiance-vllm:0.9.3`) plus the +`ggz14/radiance-vllm-mxfp4` patches, serving +`just1moremodel/Qwen3.8-27B-Uncensored-MXFP4-awq` as **ONE +tensor-parallel process across both Radeon AI PRO R9700 (gfx1201)**. +It replaced the mainline-llama.cpp layer-split deployment +([[frank-medium-llamacpp-dflash2]], SUPERSEDED 2026-09-20); the same image and +model had earlier run here as two single-GPU replicas, which is the shape most +of this page describes. -**Deployed shape: two single-GPU replicas behind an adaptive-routing proxy.** The -intended shape — one tensor-parallel process across both cards (TP=2) — cannot -launch a collective on this host. The reason is a hardware property of the -motherboard's PCIe topology, not the image, the RCCL build, or the kernel -version. The evidence is in [Why TP=2 cannot run here](#why-tp2-cannot-run-here). +**Deployed shape since 2026-09-20: one rootless Quadlet, `--tensor-parallel-size 2`.** +The ProArt B850-Creator WiFi NEO board swap put both R9700s on CPU GPP root +ports (`00:01.1 → 03:00.0` and `00:01.3 → 07:00.0`), both Gen5 x8, every +upstream bridge `AtomicOpsCap: Routing+` and both endpoints `ReqEn+` — the wall +documented in [Why TP=2 cannot run here](#why-tp2-cannot-run-here) is gone on this +board. The collective that actually runs is vLLM's R4D one-shot allreduce, which +does not use RCCL at all (TheRock RCCL has no gfx1201 device code; see +[[Dual-R9700-Cooperation]]). + +## Deployed flags (2026-09-20) + +From `dankserver/frank-medium/quadlet/frank-medium.container`: + +| Setting | Value | +|---|---| +| Model | `just1moremodel/Qwen3.8-27B-Uncensored-MXFP4-awq` | +| Speculative | `--speculative-config {"method":"dflash","model":"/models/draft","num_speculative_tokens":7}` (z-lab DFlash2-FP8) | +| Parallelism | `--tensor-parallel-size 2` (`ROCR_VISIBLE_DEVICES=0,1`) | +| Context | `--max-model-len 262144` | +| Concurrency | `--max-num-seqs 8`, chunk 8192 | +| KV | fp8 (`--kv-cache-dtype fp8`), **auto-sized — no `KV_CACHE_MEMORY_MB`** | +| Prompt cache | `--enable-prefix-caching` | +| GPU fill | `--gpu-memory-utilization 0.98` | +| Parsers | `--enable-auto-tool-choice --tool-call-parser qwen3_coder`, `--reasoning-parser qwen3` | +| Sampler floor | `--override-sampling-effects` (temp 0.7 / top_p 0.95 / top_k 20) | +| Multimodal | `--limit-mm-per-prompt '{"image": 8}'` | +| Chat template | `qwen-fixed-v22.3.jinja` (patch dir bind-mounted, `MM_MERGE_ENGINE=AXROW_SEPARATE` for Gemma4 vision) | + +**The KV pool is auto-sized, not pinned.** The arm-R benchmark run used +`KV_CACHE_MEMORY_MB=18563072000`, which bought exactly one 262,144-token +sequence (262,720 tokens at 70,656 B/token — a profile inflated by the +8192-chunk activation peak). Production ships no such pin: the pool came up at +**943,581 tokens = 3.59× the full window**, and the boot line read +`Available KV cache memory: 18.17 GiB → GPU KV cache size: 943,581 tokens`. +Per-token cost in steady state is 19,673 B — fp8 KV across the model's 16 +full-attention layers plus the drafter's. Container RSS measured 28.4 GiB +against the host's 62 GiB and stayed flat through a 4-way burst at 512-token +max; host-wide swap 3.3 GiB, unchanged. The 2026-09-16 swap storm was the +two-replica vision shape, not this one. + +## Battery results — why this shape won (2026-09-20) + +`scripts/bench-conversation.py`, 10 real-workload prompts, `max_tokens=512`, +greedy, salted per run and per arm, service stopped between arms +(`scripts/bench-conversation.py --host http://127.0.0.1:7770 --burst 4`): + +| Arm | Shape | Decode (geomean) | TTFT (mean) | Prefill (geomean) | Burst-4 aggregate | +|---|---|---|---|---|---| +| I | llama.cpp layer split 32:33 + DFlash2 Q4_K_M drafter | 45.7 t/s | 0.72 s | ~530 t/s | 71.7 t/s (26.7/stream) | +| L | llama.cpp `--split-mode tensor` 1:1, drafterless | 30.5 t/s | 0.71 s | — | 54.3 t/s | +| **R** | **vllm-radiance TP=2 + DFlash2-FP8** | **95.8 t/s** | **0.21 s** | **1493.6 t/s** | **259.4 t/s (65.6/stream)** | + +Re-measured against the production unit after deploy: geomean decode 92.4 t/s, +mean TTFT 0.22 s, burst-4 aggregate 248.9 t/s — within noise of arm R. + +Honest caveat: arm R carries MXFP4 (4-bit) where the llama arms carry Q8_0 +(8-bit), so part of the win is quantization, not tensor parallelism alone. Arm +L exists to show that llama.cpp's own TP is not the answer here regardless — +it is slower than its own layer split, and cannot carry the drafter at all. + +## Verified capabilities (2026-09-20, against the live endpoint) + +- `/v1/models` → `id: frank-medium`; `/health` → 200. +- **Tool calls**: `finish_reason: tool_calls` via `qwen3_coder`. The harness + drives a bash tool through this endpoint end to end. +- **Reasoning**: `reasoning_effort` accepts `none`/`low`/`medium`/`high` + natively (vLLM's `ReasoningEffort`); thinking arrives in the `reasoning` + field, NOT llama.cpp's `reasoning_content`. `max_tokens` counts visible + content only; with no reasoning budget the model still spends it, so a tiny + budget returns `content: null` with `finish_reason: length`. +- **Vision works** despite `language_model_only: true` in `config.json` — the + Gemma4 merge path answers image requests (~83 prompt tokens for a small + synthetic), correctly identifying shape and colour on held-out images. + `models.yml` therefore lists this endpoint as `input: [text, image]`. +- Drafter is live: accept length 2.9–4.3 tokens per draft, acceptance ~0.60. + +## Rollback + +The llama.cpp layer-split trio is archived in `scripts/.AGENTTRASH/ +20260920-llama-layersplit/` (`frank-medium.service`, `frank-medium.env`, +`serve-frank-medium.sh`) and the runtime + Q8_0 payload remain on disk: + +1. `git revert` the cutover commit. +2. `deploy.sh dankserver --service frank-medium` (re-installs and re-enables the root unit). +3. Or by hand: restore the three files, move the unit symlink back into `/etc/systemd/system/`, `sudo systemctl daemon-reload && sudo systemctl unmask frank-medium && sudo systemctl start frank-medium`. +4. Gate: `curl -s http://192.168.0.235:7770/health` → 200. + +## R4D vs RCCL + +vLLM's R4D one-shot allreduce bypasses RCCL entirely because TheRock RCCL +builds lack gfx1201 device code (`invalid device function`). The Ubuntu +RCCL 2.27 / `librccl1` 7.1.0 build does load gfx1201 kernels — that is what +`scripts/build-llama-rdna4.sh` with `GGML_HIP_RCCL=ON` links +(`build-rdna4-rocm714-rccl/`) — so llama.cpp's tensor mode has a real +collective too. It is simply the slower shape. + +> **The sections from here down describe the 2026-09-16 → 2026-09-19 era: two +> single-GPU replicas behind an adaptive-routing proxy, on the TUF GAMING +> B650-E.** The deployed shape is above; this is the evidence trail that made +> replicas necessary then and what the 2026-09-20 board swap changed. ## Architecture @@ -71,6 +164,14 @@ host would restart forever without ever becoming healthy. ## Why TP=2 cannot run here +> **Resolved 2026-09-20.** Everything below is true of the **TUF GAMING +> B650-E WIFI**, whose second card sat behind chipset bridges advertising +> `AtomicOpsCap: Routing-`. The ProArt B850-Creator WiFi NEO swap moved both +> cards onto CPU GPP root ports (`00:01.1 → 03:00.0`, `00:01.3 → 07:00.0`, Gen5 +> x8, every hop `Routing+`, both endpoints `ReqEn+`), and TP=2 now boots and +> serves. The measurement verdict against the alternatives is in +> [[Dual-R9700-Cooperation]]. + ### Symptom Any two-rank collective dies at launch: @@ -83,14 +184,16 @@ Any two-rank collective dies at launch: With the runtime's own API log (`AMD_LOG_LEVEL=3`) the failing call is explicit: ``` -ShaderName : ncclDevKernel_Generic_4(ncclDevKernelArgsStorage<4096ul>) -:1:rocvirtual.cpp :4208: Pcie atomics not enabled, hostcall not supported -:1:rocvirtual.cpp :4636: AQL dispatch failed! -:3:hip_module.cpp :893 : hipLaunchKernel: Returned hipErrorIllegalState +[ShaderName : ncclDevKernel_Generic_4(ncclDevKernelArgsStorage<4096ul>)] +[ :1:rocvirtual.cpp :4208: Pcie atomics not enabled, hostcall not supported] +[ :1:rocvirtual.cpp :4636: AQL dispatch failed!] +[ :3:hip_module.cpp :893 : hipLaunchKernel: Returned hipErrorIllegalState] ``` ROCclr refuses to hand the kernel a hostcall buffer when the device has no -PCIe atomics (`rocclr/device/rocm/rocvirtual.cpp:3963`), and the launch aborts. +PCIe atomics (`pcie_atomics_` is true for the device init, and ROCr passes +that buffer only when `pcie_atomics_` is true; otherwise it returns "not +supported" and the dispatch fails) — and the launch aborts. `hipErrorIllegalState` is that refusal, not a driver fault. ### Chain of causation @@ -99,15 +202,15 @@ PCIe atomics (`rocclr/device/rocm/rocvirtual.cpp:3963`), and the launch aborts. 2. ROCr passes that buffer only when `pcie_atomics_` is true for the device; otherwise it returns "not supported" and the dispatch fails. 3. `pcie_atomics_` is set once, at device init, from the HSA link info between - the CPU agent and the GPU (`rocclr/device/rocm/rocdevice.cpp:186`, - `Device::checkAtomicSupport`). It is not re-read per process. + the CPU agent and the GPU (`Device::checkAtomicSupport`). It is not re-read + per process. 4. The KFD driver populates that link info from `pci_enable_atomic_ops_to_root()`, which — per the PCIe spec and the kernel's implementation — requires **every upstream bridge** between the device and its root port to advertise `AtomicOp Routing` capability (`drivers/pci/pci.c`). -### The hardware difference between the two cards +The hardware difference between the two cards: | Card | PCIe chain (endpoint → root port) | `AtomicOpsCap` on every hop | AtomicOpsCtl | |---|---|---|---| @@ -135,7 +238,7 @@ boot with the write already in place) would change it — and even then the two | P2P hardware | fine: 45.3 GB/s bidirectional copy between the two cards; both cards pass `rocm-bandwidth-test` | | The shipped librccl | a from-source rebuild of `ROCm/rccl` develop (with local fixes for that branch's dangling references) reproduces the same failure at the same call path — the library is not at fault | | vLLM/pynccl | a bare two-rank `torch.distributed` allreduce with no vLLM involved fails the same way; single-rank collectives succeed on both cards (NCCL short-circuits at `world_size=1`, which is why a one-card test proves nothing) | -| Transport knobs | `NCCL_PROTO=Simple`, `NCCL_P2P_DISABLE`, `NCCL_SHM_DISABLE`, `NCCL_CUMEM_ENABLE=0`, MSCCL off, channel counts, launch modes, `HSA_ENABLE_SDMA=0` — all identical | +| Transport knobs | `NCCL_PROTO=Simple`, `P2P_DISABLE`, `SHM_DISABLE`, `CUMEM_ENABLE=0`, MSCCL off, channel counts, launch modes, `HSA_ENABLE_SDMA=0` — all identical | | Image/support matrix | the same image on a different host with the same kernel (Proxmox VM, Codeberg issue #22) fails byte-identically | ### What would fix it @@ -145,7 +248,10 @@ boot with the write already in place) would change it — and even then the two true TP=2. On this AM5 platform the CPU provides the x16 slot plus x4 lanes, so a second x16-class card necessarily lands on the chipset path — a platform with more CPU lanes (Threadripper/EPYC) is the structural answer. -- Until then, **two replicas** are how both cards serve. +- **Done 2026-09-20 — this is exactly what happened.** The ProArt + B850-Creator WiFi NEO routes both slots to CPU root ports, the atomics + condition is satisfied, and TP=2 is the deployed shape. The Threadripper/EPYC + argument was correct about the old board and is now moot. ## Routing @@ -159,7 +265,7 @@ The proxy decides per request, from `proxy/routing.py` (policy) and subagents — spreads across the cards by counter, so both prefill in parallel. Measured on this host, 90k-token contexts and 15k-token prompts, `vllm bench` -plus a small sequential-turn client: +plus a sequential-turn client: | strategy | cold 16-request burst | warm-turn TTFT (4 turns × 2 families) | |---|--:|--:| @@ -187,13 +293,16 @@ Both replicas, uniform except GPU index and port: | Knob | Value | Why | |---|---|---| | `TP` | 1 | one card per replica | -| `MAXLEN` | 114688 | the largest shape that boots on one card: 262144 needs 9.61 GiB of KV against 5.14 available, and 131072 needs 5.58 against 5.22 | -| `KV_MEM` | 0 | passed through literally as `--kv-cache-memory 0`, which the image's patched KV sizing reads as "profile this shape"; the upstream pin (2x7551-32624) is a TP=2/262144 measurement and is invalid here. **Do not blank the variable instead of passing 0**: with the flag omitted vLLM sizes the cache from `GPU_UTIL` alone and the KV allocation dies with `torch.OutOfMemoryError` (measured: 2.16 GiB requested, 116 MiB free, 29.34 GiB already held) | +| `MAXLEN` | 114688 | the largest shape that boots on one card: 262144 needs 9.61 GiB of KV against 5.21 GiB available, and 131072 needs 5.58 GiB against 5.22 | +| `KV_MEM` | 0 | passed through literally as `--kv-cache-memory 0`, which the image's patched KV sizing reads as "profile this shape"; the upstream pin (2x7551-32624) is a TP=2 measurement and is invalid here. **Do not blank the variable instead of passing 0**: with the flag omitted vLLM sizes the cache from `GPU_UTIL` alone and the KV allocation dies with `torch.OutOfMemoryError` (measured: 2.16 GiB requested, 116 MiB free, 29.34 GiB already held) | | `MAXSEQS` | 4 | matches the per-replica share of the fleet's concurrency | -| `CHUNK` | 8192 | prefill chunk (upstream default), **coupled to the context**: the prefill arena grows with the chunk size and shares the device budget with the KV cache. Measured: `CHUNK=16384` leaves 4.22 GiB of KV against the 5.21 GiB that 114688 context needs, and the engine refuses to start (`To serve at least one request with the model's max seq len (114688), 5.21 GiB KV cache is needed, which is larger than the available KV cache memory (4.22 GiB)`). Raising CHUNK therefore means cutting `MAXLEN`; single-card prefill measured ≈2.5k tok/s at 8192 (~15k-token prompt, 5992 ms TTFT), so the trade was not worth taking | +| `CHUNK` | 8192 | prefill chunk (upstream default), **coupled to the context**: the prefill arena grows with the chunk size and shares the device budget with the KV cache. Measured: `CHUNK=16384` leaves 4.22 GiB of KV against the 5.21 GiB that 114688 context needs, and the engine refuses to start (`To serve at least one request with the model's max seq len (114688), 5.21 GiB KV cache is needed, which is larger than the available KV cache memory (4.22 GiB)`). Raising CHUNK therefore means cutting `MAXLEN`; single-card prefill measured ≈2.5k tok/s at 8192 (~15k-token prompt, 5992 ms TTFT) | | `GPU_UTIL` | 0.98 | upstream default; the card is dedicated | -| `SPEC_METHOD` / `SPEC` | dflash / 7 | the DFlash2-FP8 block-diffusion drafter. Depth 7 is upstream's production default and was re-measured here on a code corpus built from this repo (see [Speculative depth](#speculative-depth)); depth 5 wins batch throughput, 7 wins single-stream latency, and this fleet is interactive | -| `SNAP` / `DRAFTER` | `/models/Qwen3.8-27B-Uncensored-MXFP4-awq` / `/models/Qwen3.8-27B-DFlash2-FP8` | the served checkpoint and its drafter | +| `SPEC_METHOD` / `SPEC` | dflash / 7 | the z-lab DFlash2-FP8 block-diffusion drafter. Depth 7 is upstream's production default and was re-measured here on a code corpus built from this repo (see [Speculative depth](#speculative-depth)); depth 5 wins batch throughput, 7 wins single-stream latency, and this fleet is interactive | +| `spec-draft-device` | `ROCm1` | the drafter rides the card that ends up holding the target's last layers | +| `temp` / `top-p` / `top-k` | `0.7` / `0.95` / `20` | the values the vLLM predecessor served on this endpoint | +| `reasoning-format` / `reasoning-budget` | `deepseek` / `-1` | trace into `reasoning_content`, unlimited | +| `mmproj` | `mmproj-Qwen3.8-27B-Uncensored-f16.gguf` (beside the target) | vision enabled; this build has NO autoload, so the flag is explicit and the serve script refuses to start without the file | Mounts are the TP=2 unit's minus nothing: `/models`, the HF cache, the shared compile cache, `/patches` (the pinned radiance clone; its patches are applied @@ -202,7 +311,7 @@ at every container start), `/r4d` (the patched libr4d — the image's shipped the entrypoint/healthcheck/proxy scripts mounted read-only out of `/home/dank/serverAppConfigs`. -The healthcheck reads `PORT`, so one probe serves the replicas (:7771/:7772), +The healthcheck reads `PORT`, so one probe serves the replicas (:7770), the proxy (:7770) and the TP=2 target. ### Boot persistence, verified by rebooting @@ -216,7 +325,8 @@ sudo reboot # unattended; ~2 min 14 s to graphical.target # ... no manual step at any point ... systemctl --user is-active frank-medium-a frank-medium-b frank-medium-proxy -> active active active (containers up 59 s after boot) -curl http://127.0.0.1:7770/health -> both replicas UP ~3.5 min after boot +# ... +curl http://127.0.0.1:7770/health # both replicas UP ~3.5 min after boot ``` Why it comes back: each unit's `[Install] WantedBy=default.target` — the generator diff --git a/serverAppConfigs-docs/LLM/index.md b/serverAppConfigs-docs/LLM/index.md index b1d08b8..e365f87 100644 --- a/serverAppConfigs-docs/LLM/index.md +++ b/serverAppConfigs-docs/LLM/index.md @@ -1,13 +1,13 @@ # LLM Fleet — Knowledge Base -Documentation for the LLM inference fleet on the two hosts (2026-09-19): -**mainline llama.cpp on Dankserver** serving frank-medium as one layer-split -process across both Radeon AI PRO R9700 cards (orcarouter Qwen3.8-27B- -Uncensored Q8_0 + the z-lab DFlash2 Q4_K_M drafter, balanced 32:33), and TWO -endpoints on Dankclaw — the CIRU v4.4.1 runtime (frank-large, jcbtc -Qwen3.8-Flash-CIRU-STRIX-Orca w4b on the gfx1151 iGPU, port 7770) and mainline -llama.cpp (frank-small, HauhauCS Gemma4-12B QAT Q4_K_M with MTP and vision on -the RTX 3090, port 7771). +Documentation for the LLM inference fleet on the two hosts (2026-09-20): +**vllm-radiance on Dankserver** serving frank-medium as ONE tensor-parallel +process across both Radeon AI PRO R9700 cards (just1moremodel +Qwen3.8-27B-Uncensored MXFP4-awq + the z-lab DFlash2-FP8 drafter, TP=2 over the +R4D one-shot allreduce), and TWO endpoints on Dankclaw — the CIRU v4.4.1 +runtime (frank-large, jcbtc Qwen3.8-Flash-CIRU-STRIX-Orca w4b on the gfx1151 +iGPU, port 7770) and mainline llama.cpp (frank-small, HauhauCS Gemma4-12B QAT +Q4_K_M with MTP and vision on the RTX 3090, port 7771). > 2026-08-22: the former `vllmScripts` repository is merged into the > serverAppConfigs repository. This knowledge base moved from the old repo's @@ -21,10 +21,10 @@ graph LR subgraph Dankserver[AMD Dankserver - Ubuntu 26.04] A[2x Radeon AI PRO R9700 gfx1201, 32 GiB each] - B2[llama.cpp, layer split + B2[vllm-radiance 0.9.3, TP=2 frank-medium, port 7770] - C[orcarouter Qwen3.8-27B Q8_0 + DFlash2 Q4_K_M -ONE process on both cards, 2x163840 ctx, balanced 32:33] + C[Qwen3.8-27B MXFP4-awq + DFlash2-FP8 +ONE process on both cards, 262144 ctx, up to 8 seqs] A --> B2 --> C end @@ -46,6 +46,7 @@ frank-small, port 7771] CLI[LLM Clients / API] -->|HTTP :7770| B2 CLI -->|HTTP :7770| E CLI -->|HTTP :7771| G +``` ## Servers @@ -56,21 +57,25 @@ frank-small, port 7771] ## Active Deployment -- [[frank-medium-llamacpp-dflash2]] — the ACTIVE frank-medium runbook since - 2026-09-16 (model swapped 2026-09-19): mainline llama.cpp serving - orcarouter/Qwen3.8-27B-Uncensored-GGUF at Q8_0 with the z-lab DFlash2 Q4_K_M - drafter on Dankserver's 2x Radeon AI PRO R9700, as ONE layer-split process - behind :7770 (tensor parallelism was impossible on the old board's second - card; the 2026-09-20 swap cleared that gate but the runtime still ships - RCCL-less and the collective is unprobed), balanced 32:33 over two 163,840-token - slots -- [[frank-medium-radiance-mxfp4]] — RETIRED 2026-09-16, one day after it was - deployed: the vllm-radiance MXFP4 stack (stilldeadcode/vllm-radiance:0.9.3 + +- [[frank-medium-radiance-mxfp4]] — the ACTIVE frank-medium runbook since + 2026-09-20: vllm-radiance MXFP4 (stilldeadcode/vllm-radiance:0.9.3 + ggz14/radiance-vllm-mxfp4 patches) serving - just1moremodel/Qwen3.8-27B-Uncensored-MXFP4-awq as two single-GPU replicas - behind a round-robin proxy; kept as the record of the deployment it - succeeded, plus the PCIe-atomics evidence that ruled out TP=2 on the previous - board — that gate cleared on 2026-09-20, see [[Dual-R9700-Cooperation]] + just1moremodel/Qwen3.8-27B-Uncensored-MXFP4-awq with the z-lab DFlash2-FP8 + drafter as ONE tensor-parallel process (TP=2) behind :7770 — the three-arm + battery that chose it, the auto-sized 943,581-token KV pool, verified + capabilities (tools, reasoning, vision), and the record of the 2026-09-16 + two-replica era +- [[frank-medium-llamacpp-dflash2]] — RETIRED 2026-09-16 → 2026-09-20: mainline + llama.cpp serving orcarouter/Qwen3.8-27B-Uncensored-GGUF at Q8_0 with the + DFlash2 Q4_K_M drafter as ONE layer-split process (32:33 over two + 163,840-token slots); superseded by the radiance TP=2 cutover, and the + rollback target. Keeps the batch/ubatch optimum curve and the per-layer split + arithmetic +- [[Dual-R9700-Cooperation]] — whether the two R9700s can serve ONE model: the + RCCL/PCIe-atomics wall on the old TUF GAMING B650-E, the 2026-09-20 ProArt + B850-Creator x8/x8 swap that cleared it, and the measured three-way verdict + (radiance TP=2 95.8 t/s decode vs layer split 45.7 vs llama tensor mode 30.5) + that put TP=2 in production - [[frank-medium-rocmfpx]] — PRIOR frank-medium deployment (llama.cpp era, 2026-09-15): charlie12345/ROCmFPX serving kingjones777/Qwen3.8-27B-ROCmFPX-Q8_0-AGENT-GGUF; kept as the record of the diff --git a/serverAppConfigs-docs/index.md b/serverAppConfigs-docs/index.md index 56a7d3c..8d1e2cd 100644 --- a/serverAppConfigs-docs/index.md +++ b/serverAppConfigs-docs/index.md @@ -115,26 +115,22 @@ The LLM inference fleet on the two hosts. Full index: - [[deployment]] — unified deploy and update process for both servers - [[frank-redo-2026-08-17]] — the 2026-08-17 topology change -- [[frank-medium-llamacpp-dflash2]] — the ACTIVE frank-medium runbook since - 2026-09-16 (model swapped 2026-09-19): mainline llama.cpp (gfx1201 HIP build) - serving orcarouter/Qwen3.8-27B-Uncensored-GGUF at Q8_0 with the DFlash2 - drafter (z-lab/Qwen3.8-27B-DFlash2-GGUF at Q4_K_M) on Dankserver's 2x Radeon - AI PRO R9700 as one layer-split process behind the :7770 endpoint, balanced - 32:33 over two 163,840-token slots — no tensor parallelism: the runtime ships - RCCL-less, and the collective has not been re-probed since the 2026-09-20 - board swap cleared the atomics gate -- [[frank-medium-radiance-mxfp4]] — RETIRED 2026-09-16: the vllm-radiance - MXFP4 stack serving just1moremodel/Qwen3.8-27B-Uncensored-MXFP4-awq on - Dankserver's 2x Radeon AI PRO R9700 as two single-GPU replicas behind a - round-robin proxy; kept as the record of the deployment - [[frank-medium-llamacpp-dflash2]] replaced, plus the PCIe-atomics evidence - that ruled out TP=2 on the previous board (gate cleared 2026-09-20) -- [[Dual-R9700-Cooperation]] — why the two R9700s *could not* run tensor-parallel - together: the PCIe-atomics gate quoted from ROCclr, the measured RCCL matrix - (collectives *and* P2P `send`/`recv` both failed on card #2, which ruled out - pipeline parallelism too), what was closed, and the re-measured 2026-09-20 - topology after the ProArt B850-Creator x8/x8 swap — both chains `Routing+`, - both endpoints `ReqEn+`, so TP=2 is unblocked but still unprobed +- [[frank-medium-radiance-mxfp4]] — the ACTIVE frank-medium runbook since + 2026-09-20: vllm-radiance MXFP4 as ONE tensor-parallel process (TP=2 over the + R4D one-shot allreduce) serving just1moremodel/Qwen3.8-27B-Uncensored-MXFP4-awq + with the z-lab DFlash2-FP8 drafter on Dankserver's 2x Radeon AI PRO R9700 + behind the :7770 endpoint — deployed flags, the three-arm battery that chose + it, verified capabilities, and the record of the 2026-09-16 two-replica era +- [[frank-medium-llamacpp-dflash2]] — RETIRED 2026-09-16 → 2026-09-20: + mainline llama.cpp (gfx1201 HIP build) serving orcarouter Qwen3.8-27B at + Q8_0 with the DFlash2 drafter as ONE layer-split process (32:33, two + 163,840-token slots); holds the batch/ubatch optimum curve and the + per-layer split arithmetic the rollback recipe points back to +- [[Dual-R9700-Cooperation]] — whether the two R9700s can run ONE model: the + RCCL/PCIe-atomics evidence on the old TUF GAMING B650-E (which closed tensor + parallelism too), what the 2026-09-20 ProArt B850-Creator x8/x8 swap changed + — both chains `Routing+`, both endpoints `ReqEn+` — and the measured + three-way verdict: radiance TP=2 won and is the deployed shape - [[frank-medium-rocmfpx]] — PRIOR frank-medium deployment (llama.cpp era): charlie12345/ROCmFPX serving kingjones777/ Qwen3.8-27B-ROCmFPX-Q8_0-AGENT-GGUF; kept as the record of the runtime it diff --git a/serverAppConfigs-docs/log.md b/serverAppConfigs-docs/log.md index f4d4e05..d24af48 100644 --- a/serverAppConfigs-docs/log.md +++ b/serverAppConfigs-docs/log.md @@ -11,6 +11,69 @@ timestamp: 2026-09-14 # Bundle Change Log +## 2026-09-20 — frank-medium cut over to radiance TP=2; monitoring follows the runtime + +- **Measured first, then cut over.** Three arms of `scripts/bench-conversation.py` + (10 real-workload prompts, `max_tokens=512`, greedy, salted per arm, service + stopped between arms per the Benchmarking Policy): llama.cpp layer split 32:33 + + DFlash2 Q4_K_M **45.7 t/s** decode geomean / 0.72 s TTFT / 71.7 t/s burst-4; + llama.cpp `--split-mode tensor` 1:1 drafterless **30.5** / 0.71 / 54.3; + vllm-radiance TP=2 + DFlash2-FP8 **95.8** / 0.21 / 259.4 (1493.6 t/s prefill). + Honest caveat recorded everywhere: the winning arm is also 4-bit where the + llama arms are 8-bit, so part of the margin is quantization, not parallelism. +- **RCCL built for the question.** `scripts/build-llama-rdna4.sh` takes + `GGML_HIP_RCCL` now; the RCCL-backed `build-rdna4-rocm714-rccl` boots llama.cpp + tensor mode with a real collective, which is what made arm L a fair test. + vLLM's own collective is R4D one-shot, not RCCL — TheRock's RCCL has no gfx1201 + device code (`invalid device function`). +- **Deploy.** `deploy.sh dankserver --service frank-medium`: the llama.cpp root + unit's symlink moved to `~/.AGENTTRASH/20260920-llama-layersplit-frank-medium/` + (never `systemctl disable` — it deletes the file), the Quadlet installed and + enabled, boot in 181 s, `/health` green. Post-deploy re-measure reproduced the + bench: 92.4 t/s, 0.22 s TTFT, 248.9 t/s burst-4. +- **KV pool is auto-sized, not pinned.** Production ships no `KV_CACHE_MEMORY_MB`: + the pool came up at **943,581 tokens = 3.59× the 262,144 window**, container RSS + flat at 28.4 GiB through a 4-way burst, host swap unchanged at 3.3 GiB. The + 18,563,072,000-byte pin was an arm-R measurement artifact (one full-context + sequence), not the deployed shape. +- **Capabilities verified against the live endpoint, not inferred**: `/v1/models`, + tool calls (`qwen3_coder`, harness drove a real bash call through it), + `reasoning_effort` none/low/medium/high with thinking in `reasoning`, drafter + accept length 2.9–4.3, and **vision works** despite `language_model_only: true` + in `config.json` — the model identified shape and colour on held-out synthetic + images. `~/.omp/agent/models.yml` therefore lists `input: [text, image]`, + `contextWindow: 262144`, `maxTokens: 32768` (compaction gap 183,500 + 32,768 + ≤ 262,144). +- **Monitoring cut over with the runtime.** `shared/prometheus/rules/llm-fleet.yml` + now spans two namespaces — `vllm:*` for frank-medium, `llamacpp:*` for the + Dankclaw pair — with 7 alerts + 2 recording rules; KV-saturation and preemption + pressure returned (vLLM exports both), and the two engine-independent rules OR + the families with per-family traffic floors. Every expression validated against + live Prometheus. **Two scrape targets were red by construction and are fixed**: + frank-small and frank-large are *host processes* on Dankclaw and netavark DNATs + only published ports, so both are now addressed as `host.containers.internal`. + Known gap: the provisioned Grafana dashboard is still keyed to `llamacpp:*`, so + frank-medium's panels are blank pending a re-cut. +- **Network decision.** `eno2` (5GbE, 192.168.0.247) kept, `eno1` pinned primary + via metric 100 vs 200 in `scripts/dankserver-route-primary.sh`; applied with + `nmcli device reapply` (there is no `nmcli connection reapply` in NM 1.54). +- **Docs.** [[frank-medium-radiance-mxfp4]] is the ACTIVE runbook (deployed flags, + battery, capabilities, rollback, with the replica-era sections labelled); + [[frank-medium-llamacpp-dflash2]] carries the SUPERSEDED banner and past-tense + lead; [[Dual-R9700-Cooperation]] now states the measured verdict instead of the + open question; [[Observability]] records the namespace split and the + netavark/DNAT lesson; `AGENTS.md` topology, frank-medium section, Model Config, + Benchmarking Policy (frank-medium is a **user** Quadlet now — `systemctl --user + stop/mask`) and the runbook index all flipped. +- **Doc-hygiene incident worth repeating.** Two parallel doc agents left the same + three wounds twice: prose prepended **above** the `---` frontmatter opener, + whole body sections duplicated wholesale, and a literal + `"<|channel>}…"` token pasted into a runbook. `check-vault-links.py` + catches only unresolved links, not structure — so the fix was `git checkout + HEAD --` the destroyed index and re-apply the flips by hand, with the agent + versions moved to `.AGENTTRASH/20260920-index-dupes/`. After any agent pass over + docs: re-check frontmatter is first, headings unique, and links resolve. + ## 2026-09-20 — dankserver board swap: the PCIe-atomics wall is gone - **Hardware.** dankserver now runs an **ASUS ProArt B850-Creator WiFi NEO** (was TUF GAMING B650-E WIFI), same Ryzen 7 7700X and same 2x R9700. The board @@ -1033,3 +1096,83 @@ timestamp: 2026-09-14 `--ctx-checkpoints`; this binary's `--help` says **32**, so the 0 is a deliberate deviation. Fixed in the env comment and in the runbook's flag table. + +## 2026-09-20 — frank-medium cut over to radiance TP=2; llama layer-split retired +- **Measurement.** Three arms, one salted battery (`scripts/bench-conversation.py`, + 10 prompts, streaming, TTFT + decode tok/s, `--burst N`), the service stopped + and masked per the benchmarking policy for every arm. radiance TP=2: decode + geomean 95.8 t/s, TTFT 0.21 s, prefill geomean 1493.6 t/s, burst-4 aggregate + 259.4 t/s (65.6 per stream). llama.cpp `--split-mode tensor` 1:1: 30.5 t/s. + llama.cpp layer split 32:33 (the incumbent): 45.7 t/s, 0.72 s, 71.7 t/s burst. + Radiance won every axis; commit `c211665` cut the endpoint over. +- **The pre-probe came out of the harness first.** A warm prefix-cache hit hid + prefill, so the first row of every arm had been measuring the cache, not the + engine. +- **llama.cpp tensor mode cannot carry the drafter on this build.** `--split-mode + tensor` plus the DFlash2 drafter aborts at `ggml-backend.cpp:941` (a weight + pre-allocated on a non-primary device has no backend when `n_copies == 1`), so + arm L ran with NO speculative decoding — its 30.5 t/s is therefore not a + like-for-like against radiance's spec-decoded 95.8, and is reported that way in + [[Dual-R9700-Cooperation]]. `--split-mode row` is SYCL-only (it needs + `ggml_backend_split_buffer_type`); `tensor` is the HIP/CUDA mode. +- **A collective HAS been dispatched on this board since the swap**, which + supersedes the "unblocked, not proven" line in the entry above. + `scripts/build-llama-rdna4.sh` now takes `GGML_HIP_RCCL=${GGML_HIP_RCCL:-OFF}` + and bundles `librccl.so*` + `librocm-core` when ON; the ON build + (`build-rdna4-rocm714-rccl`) is what ran arm L. Production stays OFF. Ubuntu + RCCL 2.27 carries gfx1201 device code; TheRock's does not ("invalid device + function"), which is why radiance ships the collective-free R4D one-shot + allreduce instead of depending on RCCL at all. +- **Deploy.** `deploy_llm_medium` in `scripts/deploy-remote.sh` gates on image + tag, MXFP4 checkpoint, drafter, patched `libr4d`, and the chat template; stops + and trashes the root llama unit (the relinked symlink is MOVED, never + `systemctl disable`, which would delete the file); waits for 7770 to be + released; installs the quadlet; waits for container health. Deployed healthy in + 181 s at `max_model_len` 262144, TP=2, 8 conversations, DFlash2 depth 7. +- **The KV pool ships auto-sized.** The unit sets no `KV_CACHE_MEMORY_MB`, so the + engine sized the pool itself: 943,581 tokens = 3.59 concurrent full 262,144-token + conversations. Under a 4-way burst the container cgroup stayed flat at 28.4 GiB + RAM and 3.3 GiB swap with host MemAvailable ~48 GiB, so the 2026-09-16 swap + storm (measured on TWO vision-carrying replicas at ~943k each) does not + reproduce on this shape. Arm R ran the explicit 18563072000 pin — 262,720 + tokens, 1.00x full window — and production prefers the 3.59x. +- **Capabilities verified live rather than assumed.** Tool calls return + `tool_calls` with `finish_reason: tool_calls` under + `--tool-call-parser qwen3_coder`. `reasoning_effort` low/medium/high/none all + answer 200, and both `none` and `chat_template_kwargs.enable_thinking=false` + switch thinking off, so this endpoint needs no `reasoningEffortMap` (that + workaround belongs to Qwen's restricted template on the Dankclaw endpoints). + Thinking arrives as vLLM's `reasoning`, not llama.cpp's `reasoning_content`. + **Vision works**: the loader installs the Gemma4 vision path and the endpoint + answered two held-out synthetic images correctly ("This is a red circle." / + "This is a blue rectangle."), so the `language_model_only` → text-only premise + written earlier today was wrong and `models.yml` keeps `input: [text, image]`. +- **Production reproduces the winning arm**: same battery, 92.4 t/s decode + geomean, 0.22 s TTFT, 1213.3 t/s prefill, 248.9 t/s burst-4 — arm R within + noise. +- **Harness.** `~/.omp/agent/models.yml` frank-medium now declares + `contextWindow: 262144` (the pool is 3.59x the window and preempts rather than + refusing, so the window is the honest number), `maxTokens: 32768` inside the + compaction gap, `input: [text, image]`, no effort map. A + `omp -p --no-session --model frank-medium` tool round trip returned the + command's output. +- **Monitoring cutover.** `shared/prometheus/rules/llm-fleet.yml` gained the vllm: + half — `LlmRequestsWaiting`, `LlmKvCacheSaturated`, + `job:llm_vllm_prefix_cache_reuse:rate5m`, `job:llm_spec_accept_length:rate5m` — + and the two existing collapse/spec alerts now cover both namespaces with a + traffic floor on each side. Every expression was run against the live + Prometheus; the accept-length rule answers 4.09 for frank-medium right now. + `shared/prometheus/prometheus.yml` also fixed a target that was red by + construction: from this bridge-networked Prometheus a host-process bind is + reachable at `host.containers.internal`, NOT at the LAN IP (netavark DNATs + published ports only), so `frank-small` had read down for days while healthy + and exporting. `frank-large` is now scraped too — it exports 19 `llamacpp:` + families including every series the rules use, contra the comment that excluded + it. +- **The two-NIC question from the entry above is decided**: `eno1` is pinned as + the primary route (metric 100) with `eno2` retained as failover (metric 200) by + `scripts/dankserver-route-primary.sh`, applied with `nmcli device reapply` + (`nmcli connection reapply` does not exist in NetworkManager 1.54). +- **Rollback.** `git revert c211665`, relink `scripts/frank-medium.service` from + `scripts/.AGENTTRASH/20260920-llama-layersplit/`, `sudo systemctl restart + frank-medium.service`. The llama runtime and the Q8_0 payload are still on disk. diff --git a/shared/homepage/docs.html b/shared/homepage/docs.html index 34481ba..b4f6359 100644 --- a/shared/homepage/docs.html +++ b/shared/homepage/docs.html @@ -47,10 +47,10 @@

frank-large — the big brain

    -
  • Model: Qwen3.8-Flash-Next, w4b quantization, served by halogen-flash-server.
    • +
  • Model: Qwen3.8-Flash CIRU-STRIX-Orca, served by CIRU v4.4.1 llama.cpp with the model's own MTP draft head.
  • Hardware: Dankclaw's Strix Halo iGPU (gfx1151), shared with the whole host.
    • -
  • Best for: long, thoughtful text conversations. 200k-token context per conversation.
    • -
  • Capacity: exactly two conversations resident at once. A third waits — politely, but it waits.
    • +
  • Best for: long, thoughtful text conversations at the model's full trained window.
    • +
  • Capacity: exactly one conversation resident at a time. A second waits — politely, but it waits.
  • Not for: images. It cannot see them.
@@ -67,11 +67,11 @@
  • Model: Qwen3.8-27B-Uncensored at MXFP4, on vllm-radiance with a DFlash2 draft head.
  • Hardware: Dankserver's two Radeon R9700s as ONE tensor-parallel engine (TP=2).
  • Best for: general chat and reasoning when the big brain is busy; the biggest pure-language model we run, and the fastest we have measured.
    • -
  • Capacity: 262k-token context, shared by up to eight conversations at once. Text only — pictures go to frank-small.
    • +
  • Capacity: 262k-token context shared by up to eight conversations at once. It can see pictures too; frank-small is the faster eye and holds four conversations.

    • Which one to pick? Screenshots and photos: frank-small. - Deep long-text work: frank-large (mind the two-seat limit). + Deep long-text work: frank-large (mind the single seat). When in doubt: frank-medium.

    diff --git a/shared/homepage/services.json b/shared/homepage/services.json index 8810bd7..a136ec4 100644 --- a/shared/homepage/services.json +++ b/shared/homepage/services.json @@ -233,7 +233,7 @@ { "name": "frank-large", "category": "user", - "description": "The big brain. Qwen3.8-Flash-Next w4b on halogen-flash-server, running on Dankclaw's Strix Halo iGPU. Text-only; holds two 200k-token conversations resident.", + "description": "The big brain. Qwen3.8-Flash CIRU-STRIX-Orca on CIRU v4.4.1 llama.cpp, running on Dankclaw's Strix Halo iGPU. Text-only; one conversation resident at a time.", "url": "", "docs": "/docs#models", "probe": "127.0.0.1:7770", diff --git a/shared/prometheus/prometheus.yml b/shared/prometheus/prometheus.yml index 675df33..3e647d8 100644 --- a/shared/prometheus/prometheus.yml +++ b/shared/prometheus/prometheus.yml @@ -69,34 +69,51 @@ scrape_configs: - "192.168.0.143:8081" # SearXNG (via the Gluetun tunnel) - "192.168.0.143:3005" # OpenWebUI - # LLM fleet. Scraped on the LAN addresses, not the guarded vhosts: these are - # machine clients and Prometheus cannot solve an Anubis challenge. - # Both LLM endpoints are llama.cpp, so both export the same llamacpp: - # counter family: prompt/decode throughput, requests_deferred (queue depth - # — the only form llama.cpp exposes the capacity wall in), the - # spec_decode_num_drafts / spec_decode_num_accepted pair (proof the drafter - # is running), and the prefix-cache pair prompt_tokens_cached_total over - # prompt_tokens_total (their rates are the reuse rate, which says whether - # pinned conversations are actually being reused). - # frank-large is deliberately NOT scraped: the halogen engine that serves it - # publishes /health, /cache and /v1/* and no Prometheus text endpoint, so a - # target here would be red by construction and would fire LlmEndpointDown - # forever. Its liveness is on the homepage (a loopback probe) and in the - # engine's own boot ledger. The remedy, when the fleet wants it, is the - # blackbox exporter already wanted for the comfyui/services probes. + # LLM fleet. Scraped on the LAN addresses where the endpoint is reachable from + # this container, not the guarded vhosts: these are machine clients and + # Prometheus cannot solve an Anubis challenge. # - # frank-small is llama.cpp (its serve script passes --metrics) and does - # export text-format counters under llamacpp: on the port its unit publishes. + # Two metric namespaces, because the fleet runs two runtimes: + # + # * vllm:* — frank-medium (vllm-radiance TP=2 since 2026-09-20): prompt and + # generation token counters, num_requests_waiting plus its reason label, + # num_preemptions_total, the kv_cache_usage_perc fill gauge, the + # prefix_cache hits/queries pair, the spec_decode drafts/accepted triple, + # and real latency histograms (time_to_first_token, inter_token, + # e2e_request_latency). + # * llamacpp:* — frank-large and frank-small. Both take --metrics and both + # were verified 2026-09-20 to export requests_deferred (the queue depth, + # the only form llama.cpp shows the capacity wall in), + # spec_decode_num_drafts_total, tokens_predicted_total, and the + # prompt_tokens_cached_total / prompt_tokens_total reuse pair. + # + # frank-large is scraped over host.containers.internal, not its own LAN address: + # this Prometheus is a bridge-networked container (Network=dankclaw_default), + # and on this netavark host a container can only reach the host's LAN IP at a + # PUBLISHED port — a host-process bind like llama-server's 0.0.0.0:7770 is + # refused at 192.168.0.143:7770 while it answers at 169.254.1.2:7770. That is + # why frank-small was red here for days (up{job="frank-small"} == 0, + # "dial tcp 192.168.0.143:7771") even though the endpoint was healthy and + # exporting: the target address was unreachable by construction, not the + # service down. Same host, same rule, so both local endpoints use the gateway. + # frank-medium stays a LAN address — it is a different machine. - job_name: "frank-medium" metrics_path: "/metrics" static_configs: - targets: ["192.168.0.235:7770"] labels: service: frank-medium - + - job_name: "frank-small" metrics_path: "/metrics" static_configs: - - targets: ["192.168.0.143:7771"] + - targets: ["host.containers.internal:7771"] labels: service: frank-small + + - job_name: "frank-large" + metrics_path: "/metrics" + static_configs: + - targets: ["host.containers.internal:7770"] + labels: + service: frank-large diff --git a/shared/prometheus/rules/llm-fleet.yml b/shared/prometheus/rules/llm-fleet.yml index a5f17c9..c43fb48 100644 --- a/shared/prometheus/rules/llm-fleet.yml +++ b/shared/prometheus/rules/llm-fleet.yml @@ -1,39 +1,64 @@ # Alerting and recording rules for the LLM fleet. # -# Every expression here is keyed to a series that EXISTS as of 2026-09-16. When -# frank-medium moved from vllm-radiance to llama.cpp the exported namespace -# changed with it (vllm: -> llamacpp:), and two signals the old file alerted on -# no longer exist in any form: +# Two metric namespaces, because the fleet runs two runtimes: # -# * vllm:kv_cache_usage_perc — llama.cpp exports no KV-fill gauge. Its -# observable consequence is queueing, which is what LlmRequestsQueueing -# watches instead. A renamed query would have been a rule that can never -# fire. -# * vllm:e2e_request_latency_seconds_* — no latency histogram either. The -# rule it fed (p95 wall clock) is retired rather than restated, and -# LlmSpecDecodeOff takes its place: the failure an operator actually -# cannot see from the outside on this deployment. +# * llamacpp:* — frank-small (Dankclaw, llama.cpp with --metrics). +# * vllm:* — frank-medium (Dankserver, vllm-radiance TP=2 since 2026-09-20). +# +# Every expression is keyed to a series that EXISTS, verified against +# 192.168.0.235:7770/metrics and 192.168.0.143:7771/metrics on 2026-09-20. +# Nothing here matches on absence: when frank-medium moved back to vLLM the +# llamacpp: selectors narrowed to frank-small rather than going vacuous, and +# the vllm: group below was added beside them, not in place of them. +# +# What each namespace can and cannot see: +# +# * KV pressure. vLLM exports a fill gauge (vllm:kv_cache_usage_perc) and a +# preemption counter; llama.cpp exports neither, so its capacity wall is +# observed as queueing (llamacpp:requests_deferred). +# * Prefix reuse. Both export a hits/queries pair, in tokens; the two +# recording rules below keep the units straight and the collapse alert +# watches both sides with one threshold. +# * Speculative decoding. Both export drafts and accepted tokens, so +# LlmSpecDecodeOff covers both runtimes. +# * Latency histograms exist only on vLLM (e2e, TTFT, inter-token). No +# p95 alert is defined for the llama.cpp side because there is nothing to +# compute one from. # # IMPORTANT: delivery. Since 2026-09-17 a firing alert reaches Frank on # Signal: Prometheus pushes to Alertmanager (dankclaw/observability/quadlet/ # alertmanager.container), whose single receiver webhooks the host-side # signal-relay user unit, which hands the text to signal-cli under the -# existing account on this host. Before that date a firing alert appeared on -# Prometheus' /alerts page, in the ALERTS metric (which the LLM fleet -# dashboard graphs) and nowhere else. +# existing account on this host. groups: - name: llm-fleet interval: 30s rules: - # Recording rule so the dashboard and the alert below share one - # expression. The exported series are counters; the rate is the reuse. + # Recording rules so the dashboard and the collapse alert below share one + # expression. Both namespaces export hits/queries pairs in TOKENS; the + # rate of the quotient is the reuse rate. Kept as two records because the + # series names differ and a vacuous joint query is worse than two honest + # ones. - record: job:llm_prefix_cache_reuse:rate5m expr: | rate(llamacpp:prompt_tokens_cached_total[5m]) / clamp_min(rate(llamacpp:prompt_tokens_total[5m]), 0.001) - # The capacity wall, in the only form llama.cpp exports it: work waiting - # for the single slot. Past here the next large request queues. + - record: job:llm_vllm_prefix_cache_reuse:rate5m + expr: | + rate(vllm:prefix_cache_hits_total[5m]) + / clamp_min(rate(vllm:prefix_cache_queries_total[5m]), 0.001) + + # Mean accepted draft length (1.0 = the drafter proposes and nothing is + # taken, so the draft round is pure overhead). Measured 3.0-4.3 on + # frank-medium at boot with the DFlash2 drafter, 2026-09-20. + - record: job:llm_spec_accept_length:rate5m + expr: | + 1 + rate(vllm:spec_decode_num_accepted_tokens_total[5m]) + / clamp_min(rate(vllm:spec_decode_num_drafts_total[5m]), 0.001) + + # The capacity wall on the llama.cpp side, in the only form it exports: + # work waiting for a slot. Past here the next large request queues. - alert: LlmRequestsQueueing expr: llamacpp:requests_deferred > 0 for: 10m @@ -46,13 +71,50 @@ groups: fleet is genuinely busy or one endpoint is carrying it alone. With --parallel 1 a second concurrent request always shows up here. + # The capacity wall on the vLLM side, in its own two terms: requests the + # scheduler has not admitted, and requests it admitted and then PREEMPTED + # (a preemption throws away the KV and re-prefills, so its rate is the + # cost of running the pool full). frank-medium auto-sizes its pool to + # 943,581 tokens = 3.59 concurrent full 262,144-token conversations, so + # saturation is four such conversations, not two. + - alert: LlmRequestsWaiting + expr: vllm:num_requests_waiting > 0 + for: 10m + labels: + severity: warning + annotations: + summary: "{{ $labels.job }}: vLLM has not admitted work for 10 minutes" + description: >- + The scheduler is holding requests back. Check the reason label on + vllm:num_requests_waiting_by_reason (capacity = no KV room, defer = + waiting for a better batch shape) and the preemption counter + vllm:num_preemptions_total. + + - alert: LlmKvCacheSaturated + expr: vllm:kv_cache_usage_perc > 0.95 + for: 10m + labels: + severity: warning + annotations: + summary: "{{ $labels.job }}: KV pool above 95 % for 10 minutes" + description: >- + The pool is full, which is where preemption and re-prefill start: + decode slows before anything errors. The pool is auto-sized by the + quadlet (no KV_CACHE_MEMORY_MB pin); the boot ledger prints the + token count — `podman logs frank-medium | grep "GPU KV cache size"` + — and it was 943,581 tokens on 2026-09-20. + # The thrash signature measured on 2026-09-16: requests keep arriving but # almost none are served from cache, which is what several concurrent - # 50-80k-token conversations do to this fleet. + # 50-80k-token conversations do to this fleet. One threshold, two + # namespaces, and a traffic floor per side so an idle endpoint cannot + # fire it on a 0/0. - alert: LlmPrefixCacheCollapse expr: >- - job:llm_prefix_cache_reuse:rate5m < 0.20 - and rate(llamacpp:prompt_tokens_total[5m]) > 0.05 + (job:llm_prefix_cache_reuse:rate5m < 0.20 + and rate(llamacpp:prompt_tokens_total[5m]) > 0.05) + or (job:llm_vllm_prefix_cache_reuse:rate5m < 0.20 + and rate(vllm:prefix_cache_queries_total[5m]) > 1) for: 15m labels: severity: info @@ -65,12 +127,14 @@ groups: # The speculative path is the one failure no client can see: the server # answers normally, just at half the speed, when the drafter is gone. - # Drafts and accepts are counters, so a rate that stays at zero while the - # endpoint is serving tokens means nothing is being drafted. + # Drafts and accepts are counters in both runtimes, so a rate that stays + # at zero while the endpoint is serving tokens means nothing is drafted. - alert: LlmSpecDecodeOff expr: >- - rate(llamacpp:spec_decode_num_drafts_total[5m]) == 0 - and rate(llamacpp:tokens_predicted_total[5m]) > 0.1 + (rate(llamacpp:spec_decode_num_drafts_total[5m]) == 0 + and rate(llamacpp:tokens_predicted_total[5m]) > 0.1) + or (rate(vllm:spec_decode_num_drafts_total[5m]) == 0 + and rate(vllm:generation_tokens_total[5m]) > 0.1) for: 15m labels: severity: warning @@ -78,11 +142,11 @@ groups: summary: "{{ $labels.job }}: serving without speculative decoding" description: >- Tokens are being produced but no draft has been proposed for 15 - minutes. On the llama.cpp endpoints that means the drafter is not - running (check the unit's log for the - "adding speculative implementation" line — draft-mtp on both - endpoints as of 2026-09-17), and the endpoint is decoding - autoregressively. + minutes. frank-small (llama.cpp) should log "adding speculative + implementation" at load; frank-medium (vllm-radiance) should be + counting vllm:spec_decode_num_drafts_total and reporting 3+ mean + accept length (job:llm_spec_accept_length:rate5m). Either way the + endpoint is decoding autoregressively. # The endpoint, not a replica: one process serves each port now, so a # restart of the unit is a scrape gap, not a failover. @@ -94,8 +158,10 @@ groups: annotations: summary: "{{ $labels.job }}: scrape target down for 2 minutes" description: >- - Prometheus cannot reach the LLM endpoint. Check the units: - `systemctl is-active frank-medium` on Dankserver (a root llama.cpp - unit) and `systemctl is-active frank-small` on Dankclaw. frank-large - is not scraped at all — the halogen engine exports no metrics — so - this alert can only ever name the endpoints that do export one. + Prometheus cannot reach the LLM endpoint. frank-medium is a + rootless quadlet: `systemctl --user is-active frank-medium` on + Dankserver, then `podman ps -a --filter name=frank-medium`. + frank-small is a root unit: `systemctl is-active frank-small` on + Dankclaw. frank-large is not scraped at all — its CIRU runtime + serves no Prometheus text endpoint — so this alert can only ever + name the endpoints that do export one. diff --git a/tests/observability_quadlet.bats b/tests/observability_quadlet.bats index 940f0a8..300f646 100755 --- a/tests/observability_quadlet.bats +++ b/tests/observability_quadlet.bats @@ -300,21 +300,23 @@ PAIRS @test "prometheus scrapes every LLM endpoint that exports metrics" { # The LLM endpoints are the services whose behaviour this fleet argues about - # most (KV pressure, prefix-cache reuse, queue depth), and vLLM exports all - # of it. If a scrape target drifts from the endpoint the units publish, - # nobody notices until someone needs the graph during an incident. + # most (KV pressure, prefix-cache reuse, queue depth). Since frank-medium + # moved to radiance/vLLM on 2026-09-20 there are two metric namespaces, and + # the three addresses differ by HOW each endpoint is reachable from a + # container: netavark DNATs *published* container ports only, so + # frank-medium — a rootless Quadlet on another host that publishes 7770 — is + # its LAN address, while the two Dankclaw endpoints are HOST processes and + # answer only as host.containers.internal. Addressing those two by LAN IP + # left both targets red by construction until the 2026-09-20 /targets audit. local cfg="$REPO_ROOT/shared/prometheus/prometheus.yml" grep -q '"192.168.0.235:7770"' "$cfg" || { echo "frank-medium not scraped"; return 1; } - grep -q '"192.168.0.143:7771"' "$cfg" || { echo "frank-small not scraped"; return 1; } - # The medium endpoint is exported by the proxy on the host network; the - # quadlet's own contract test pins that port, so name the job too. - grep -q 'job_name: "frank-medium"' "$cfg" - grep -q 'job_name: "frank-small"' "$cfg" - # frank-large is NOT scraped on purpose: the halogen engine serves - # /health, /cache and /v1/* and no metrics endpoint, so a target here would - # be red by construction and would fire LlmEndpointDown forever. Assert the - # absence, so a well-meaning edit cannot re-add a permanently-red probe. - ! grep -q '192.168.0.143:7770' "$cfg" + grep -q '"host.containers.internal:7771"' "$cfg" || { echo "frank-small not scraped"; return 1; } + grep -q '"host.containers.internal:7770"' "$cfg" || { echo "frank-large not scraped"; return 1; } + for job in frank-medium frank-small frank-large; do + grep -q "job_name: \"$job\"" "$cfg" || { echo "no scrape job for $job"; return 1; } + done + # None of them is reached through a guarded vhost: Prometheus cannot solve + # an Anubis challenge, so a franksdank.cloud target is red by construction. ! grep -qE '^\s*-\s*"?https?://[^"]*franksdank' "$cfg" } @@ -351,23 +353,46 @@ PAIRS import re, yaml d = yaml.safe_load(open('$rules')) names = [r.get('alert') or r.get('record') for g in d['groups'] for r in g['rules']] -for want in ('job:llm_prefix_cache_reuse:rate5m', 'LlmRequestsQueueing', - 'LlmPrefixCacheCollapse', 'LlmSpecDecodeOff', 'LlmEndpointDown'): +for want in ('job:llm_prefix_cache_reuse:rate5m', + 'job:llm_vllm_prefix_cache_reuse:rate5m', + 'job:llm_spec_accept_length:rate5m', + 'LlmRequestsQueueing', 'LlmRequestsWaiting', + 'LlmKvCacheSaturated', 'LlmPrefixCacheCollapse', + 'LlmSpecDecodeOff', 'LlmEndpointDown'): assert want in names, want -# Every rule must be keyed to a series that exists. The vLLM era's namespaces -# are gone (frank-medium is llama.cpp now) and a rule naming one of them -# evaluates nothing forever without erroring — the failure this seam exists for. +# Every rule must be keyed to a series that actually exists. A rule naming a +# series nobody exports evaluates nothing forever and errors never — the failure +# this seam exists for. Since 2026-09-20 two engines are scraped, so both +# namespaces are legal, but each name must be on the measured list. exprs = [r.get('expr', '') for g in d['groups'] for r in g['rules']] -assert not any('vllm:' in e for e in exprs), exprs -# ...and the llama.cpp series a rule may name are the ones the server exports -# (measured from /metrics on 2026-09-16). Anything else is a guess. +# llama.cpp families measured from /metrics on 2026-09-16 (frank-small, +# frank-large), vLLM families measured from /metrics on 2026-09-20 +# (frank-medium, radiance/vLLM). Anything else is a guess. live = {'llamacpp:prompt_tokens_total', 'llamacpp:prompt_tokens_cached_total', 'llamacpp:requests_deferred', 'llamacpp:requests_processing', 'llamacpp:spec_decode_num_drafts_total', 'llamacpp:spec_decode_num_accepted_tokens_total', - 'llamacpp:tokens_predicted_total'} -used = {m for e in exprs for m in re.findall(r'llamacpp:[a-z_0-9]+', e)} + 'llamacpp:tokens_predicted_total', + 'vllm:kv_cache_usage_perc', 'vllm:num_requests_running', + 'vllm:num_requests_waiting', 'vllm:num_preemptions_total', + 'vllm:generation_tokens_total', 'vllm:prompt_tokens_total', + 'vllm:spec_decode_num_accepted_tokens_total', + 'vllm:spec_decode_num_draft_tokens_total', + 'vllm:spec_decode_num_drafts_total', + 'vllm:prefix_cache_hits_total', 'vllm:prefix_cache_queries_total', + 'vllm:request_success_total'} +used = {m for e in exprs + for m in re.findall(r'(?:llamacpp|vllm):[a-z_0-9]+', e)} assert used <= live, used - live +# Engine-independent rules must cover BOTH families, or the cutover silently +# blinds one endpoint: the two rules that describe an engine-agnostic failure +# name a series from each namespace. +joined = '\n'.join(exprs) +for pair in (('LlmSpecDecodeOff', 'llamacpp:spec_decode_num_drafts_total', + 'vllm:spec_decode_num_drafts_total'), + ('LlmPrefixCacheCollapse', 'llamacpp:prompt_tokens_total', + 'vllm:prefix_cache_queries_total')): + assert any(pair[1] in e and pair[2] in e for e in exprs), pair[0] print('rules ok:', len(names)) " # A rule file that nothing loads evaluates nothing, and Prometheus reports