docs: frank-large Kairic Edge runbook + frank-medium clean-KV updates

- New runbook frank-large-kairic-edge-qwen38-27b.md (ACTIVE frank-large,
  Kairic Edge runtime, jcbtc Qwen3.8-27B-IU4, 262144 ctx, MTP depth 4 +
  n-gram drafting, compatibility mode)
- AGENTS.md: frank-large section + topology row + fleet contract + runbook
  index (Kairic Edge ACTIVE, unsloth RETIRED same-day); frank-medium
  section body (MXFP4 + unquantized bf16 KV, 486,464-token pool)
- LLM index + top-level index: Kairic Edge ACTIVE, unsloth RETIRED,
  system specs entry

AGENTS.md

@@ -12,7 +12,7 @@ merge absorbed the former `vllmScripts` repo, history preserved).
   Calibre-Web, Jellyfin, Plex) plus the `frank-medium` LLM service.
 - **Dankclaw** (192.168.0.143) — AI/search/dev/observability stack (SearXNG
   via Gluetun, ComfyUI, OpenWebUI, Hermes, Gitea, Grafana, Prometheus, Loki,
-  Alloy, Pi-hole) plus TWO LLM services: `frank-large` (unsloth llama.cpp prebuilt on
+  Alloy, Pi-hole) plus TWO LLM services: `frank-large` (Kairic Edge runtime on
   the gfx1151 iGPU) and `frank-small` (llama.cpp on the RTX 3090). Caddy on
   Dankclaw reverse-proxies both hosts.
 - **FrankBook-Pro** (192.168.0.112) — macOS mini running the *arr stack
@@ -25,7 +25,7 @@ merge absorbed the former `vllmScripts` repo, history preserved).
 | Target | Service | Runtime | Model | Port |
 |--------|---------|---------|-------|------|
 | Dankserver | `frank-medium` | vllm-radiance 0.9.3 (rootless Quadlet, image `localhost/radiance-vllm:0.9.3`, gfx1201) | just1moremodel Qwen3.8-27B-Uncensored-MXFP4-awq (MXFP4/quark W4A8, 19.37 GiB) with the z-lab DFlash2 external drafter (depth 7), 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, UNQUANTIZED bf16 KV (`KV_DTYPE=auto`, cut 2026-09-21 from the FP8/fp8-KV shape to test whether fp8 KV had been degrading W4A8 output quality; auto-sized 486,464-token pool = 1.86x the window), prefix caching, vision | 7770 |
-| Dankclaw | `frank-large` | unsloth llama.cpp b11030 prebuilt (ROCm gfx1151, root systemd unit) | unsloth Qwen3.8-Flash-Next UD-IQ4_XS on the gfx1151 iGPU (Strix Halo LPDDR, 114 GiB GTT), 200000 ctx single stream (1 slot), MTP depth 2 via the explicit `-md` shared-Q8_0 head, text only | 7770 |
+| Dankclaw | `frank-large` | Kairic Edge (ciru-ai/ROCmFPX v1.2, gfx1151, root systemd unit, built from source) | jcbtc Qwen3.8-27B-IU4-Kairic-Edge (IU4 W4A4, 27B dense, 26 GiB total) on the gfx1151 iGPU (Strix Halo LPDDR, 114 GiB GTT), 262144 ctx single stream (1 slot), MTP depth 4 + n-gram drafting (24/64/64), compatibility mode, 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 fastest vision endpoint | 7771 |
 
 Retired endpoints (`frank-npu`, and every prior runtime) are in
@@ -265,53 +265,55 @@ a role pointing at a provider the file does not define fails at call time. As
 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 unsloth deployment loads no
+images; `frank-large` remains text-only because its Kairic Edge deployment loads no
-vision projector (the F16 mmproj is on disk, one env flip away). Note also that
+vision projector (the model has no mmproj). 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.
 
-### frank-large — unsloth llama.cpp Qwen3.8-Flash-Next UD-IQ4_XS (Dankclaw, ACTIVE)
+### frank-large — Kairic Edge Qwen3.8-27B IU4 (W4A4) (Dankclaw, ACTIVE)
 
-The unsloth llama.cpp prebuilt `app-b11030-mix-5ff778e` (ROCm gfx1151,
+The Kairic Edge runtime (ciru-ai/ROCmFPX, branch
-`/home/dank/GitPackages/unsloth-llama-b11030/`, bundles its own ROCm runtime —
+`kairic-edge-qwen38-27b-v1.2`, commit `205a3e5`) as a **root systemd unit**
-no host SDK gate, no venv) as a **root systemd unit** (`scripts/
+(`scripts/frank-large.service`, `User=dank`), built from source
-frank-large.service`, `User=dank`), serving
+(`scripts/build-kairic-edge-gfx1151.sh`, TheRock 7.15.0a20260718 toolchain,
-`unsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ4_XS` (87.3 GiB main GGUF as three HF
+Composable Kernel `fdf4bb7f` + the gfx1151-iu4 patch), serving
-split parts, loaded natively as a split via `-m` on part 1, + a 2.6 GiB MTP head, all sha256-verified) on port
+`jcbtc/Qwen3.8-27B-IU4-Kairic-Edge` (27B dense, IU4 W4A4, 15.5 GiB main
-7770 from the gfx1151 iGPU. One stream, 200,000 ctx (`PARALLEL_SLOTS=1`,
+GGUF + 7.99 GiB FFN sidecar + 1.88 GiB GDN sidecar + 0.70 GiB GDN-Output
-operator's requested shape; the trained window is 262,144), MTP depth 2
+sidecar, all sha256-verified) on port 7770 from the gfx1151 iGPU. One
-(`SPEC_DRAFT_N_MAX=2`, the model card's default), reasoning extracted to
+stream, full 262,144 ctx (the model's native window, `PARALLEL_SLOTS=1`),
-`reasoning_content`, and **no vision projector** (the F16 mmproj is on disk,
+MTP depth 4 (`SPEC_DRAFT_N_MAX=4`) + n-gram drafting (24/64/64), reasoning
-`ENABLE_VISION=0` — one env flip to enable). It replaced the CIRU v4.4.1
+extracted to `reasoning_content` (compatibility mode — the harness needs
-Orca runtime, which had replaced halogen-flash-server.
+sampling, tools and a reasoning budget, which fast-greedy rejects), and
+**no vision projector**. It replaced the unsloth llama.cpp prebuilt
+(b11030, Qwen3.8-Flash-Next UD-IQ4_XS, 125B MoE), which had replaced the
+CIRU v4.4.1 Orca runtime.
 
-The runtime is the first with an MTP graph for the qwen4exp architecture
+The spec method is native MTP depth 4 + n-gram drafting. DFlash is NOT
-(stock ggml-org mainline has none), so the unsloth prebuilt is the
+available for this model (no `DRAFT_DFLASH` spec type in the Kairic Edge
-llama.cpp-compatible choice. The MTP head is loaded via an **explicit
+runtime). The three PromptForge sidecars (FFN, GDN, GDN-Output) are wired
-`-md`**: sidecar auto-discovery does not search the `mtp/` subfolder, and
+via the `PROMPTFORGE_*` env block (the certified runner's exact env). The
-without it `--spec-type draft-mtp` silently runs at the main model's speed.
+serve script (`scripts/serve-frank-large.sh`) validates binary → main GGUF →
-The serve script (`scripts/serve-frank-large.sh`) validates binary → main
+3 sidecars and exits with a pointer message if any is missing, then `exec`s
-GGUF → MTP head and exits with a pointer message if any is missing, then
+`llama-server` with `--jinja --alias frank-large --chat-template-kwargs
-`exec`s `llama-server` with `--jinja --alias frank-large --chat-template-
+'{"preserve_thinking":true}'` (Qwen3.8's template needs this to carry
-kwargs '{"preserve_thinking":true}'` (Qwen3.8's template needs this to
+thinking blocks across turns; a request-level value still wins).
-carry thinking blocks across turns; a request-level value still wins).
 
 The iGPU addresses **114 GiB** (the GTT aperture over the shared LPDDR,
 `gtt_total` in `/sys/class/drm/card1/device/`; `rocm-smi`'s 2 GiB "dedicated"
-is not the budget). The 87.3 GiB model is mmap'd in with `-ngl 999`; budget
+is not the budget). The 27B dense model (26 GiB total) is mmap'd in with
-at 200k ≈ 100 GiB (weights + MTP head + KV + buffers), leaving ~14 GiB of
+`-ngl 999`; budget at 262k ≈ 30 GiB (weights + KV + buffers), leaving ~84
-aperture headroom. The n-gram embedding (PLE) is inside the GGUF — no
+GiB of aperture headroom. The 8 GiB prompt-cache budget
-external PLE payload or pager, unlike the CIRU Orca packaging.
+(`CACHE_RAM=8192`) is the Kairic Edge qualified config.
 
-Fetch: `scripts/download-frank-large-unsloth.sh` (resumable, each part
+Fetch: `scripts/download-frank-large-kairic.sh` (resumable, each file
-verified against its LFS sha256 fetched live from the Hub tree API, then the
+verified against its declared byte count + sha256; `--verify-only` re-checks).
-assembled GGUF against `SHA256SUMS`; `--verify-only` re-checks).
 
-Runbook: `serverAppConfigs-docs/LLM/frank-large-unsloth-qwen38-flash-next.md`.
+Runbook: `serverAppConfigs-docs/LLM/frank-large-kairic-edge-qwen38-27b.md`.
-Rollback: [[frank-large-ciru-orca]] (payload and runtime intact on disk).
+Rollback: [[frank-large-unsloth-qwen38-flash-next]] (payload and runtime
+intact on disk).
 
 ### frank-small — llama.cpp on the RTX 3090 (Dankclaw, ACTIVE)
 
@@ -343,19 +345,19 @@ Rollback: [[frank-small-qwen38-gsq-rco]].
 
 vllm-radiance **0.9.3** (`localhost/radiance-vllm:0.9.3`, rootless **Quadlet**
 `dankserver/frank-medium/quadlet/frank-medium.container`) serving
-`orcarouter/Qwen3.8-27B-Uncensored-FP8` (FP8 E4M3 block-wise 128×128, dynamic
+`just1moremodel/Qwen3.8-27B-Uncensored-MXFP4-awq` (MXFP4/quark W4A8, 19.37
-activation quant, 30.9 GB / 7 shards) with the **z-lab DFlash2 external
+GiB) with the **z-lab DFlash2 external drafter** (`num_speculative_tokens: 7`,
-drafter** (`num_speculative_tokens: 7`, live mean accept 4.24/7) in **one
+live mean accept 4.24/7) in **one tensor-parallel process across both
-tensor-parallel process across both R9700s** (`--tensor-parallel-size 2`).
+R9700s** (`--tensor-parallel-size 2`). 262,144 ctx, `--max-num-seqs 8`, chunk
-262,144 ctx, `--max-num-seqs 8`, chunk 8192, fp8 KV, prefix caching, GPU fill
+8192, **unquantized bf16 KV** (`KV_DTYPE=auto`, cut 2026-09-21 from the
-0.98, **no KV-memory pin** — the pool auto-sized to 384,238 tokens (1.47× the
+FP8/fp8-KV shape to test whether fp8 KV had been degrading W4A8 output
-full window; the DFlash2 drafter's 2.1 GiB costs the pool vs MTP's 461,540).
+quality), prefix caching, GPU fill 0.98, **no KV-memory pin** — the pool
-DFlash2 was A/B tested against MTP self-speculation on this checkpoint and
+auto-sized to 486,464 tokens (1.86× the full window). DFlash2 was A/B tested
-wins on decode (100.0 vs 85.9 t/s) — see the runbook. Tools via `qwen3_coder`,
+against MTP self-speculation on this checkpoint and wins on decode (100.0 vs
-reasoning via `qwen3` (the field is `reasoning`, not llama.cpp's
+85.9 t/s) — see the runbook. Tools via `qwen3_coder`, reasoning via `qwen3`
-`reasoning_content`), vision through the Gemma4 merge path, chat template
+(the field is `reasoning`, not llama.cpp's `reasoning_content`), vision through
-Qwen-Sharp v22.4.0 (froggeric, repo-tracked at `dankserver/frank-medium/`,
+the Gemma4 merge path, chat template Qwen-Sharp v22.4.0 (froggeric,
-terse system prompt by default).
+repo-tracked at `dankserver/frank-medium/`, terse system prompt by default).
 
 **The entrypoint is quantization-aware.** `radiance-entrypoint.sh` reads
 `quantization_config.quant_method` from the checkpoint's `config.json` and
@@ -752,7 +754,7 @@ Active:
 
 | Service | Runbook |
 |---------|---------|
-| frank-large (unsloth llama.cpp Qwen3.8-Flash-Next UD-IQ4_XS, Dankclaw) | `serverAppConfigs-docs/LLM/frank-large-unsloth-qwen38-flash-next.md` |
+| frank-large (Kairic Edge Qwen3.8-27B IU4 W4A4, Dankclaw) | `serverAppConfigs-docs/LLM/frank-large-kairic-edge-qwen38-27b.md` |
 | frank-small (llama.cpp Gemma4-12B QAT, Dankclaw) | `serverAppConfigs-docs/LLM/frank-small-gemma4-12b.md` |
 | frank-medium (radiance TP=2 + MTP, Dankserver) | `serverAppConfigs-docs/LLM/frank-medium-radiance-mxfp4.md` |
 | frank-medium model swap (toolchain + process) | `serverAppConfigs-docs/LLM/frank-medium-model-swap.md` |
@@ -767,6 +769,7 @@ Retired (rollback targets and history):
 | ik_llama.cpp Qwen3.8-Flash-Next-Uncensored i1-Q4_K_M (`frank-large`) | Dankclaw | 2026-09-15 → 09-16 | `frank-large-ik-uncensored.md` |
 | halogen-flash-server Qwen3.8-Flash-Next w4b (`frank-large`) | Dankclaw | 2026-09-16 → 09-19 | `halogen-flash-server.md` |
 | CIRU v4.4.1 Orca Qwen3.8-Flash (`frank-large`) | Dankclaw | 2026-09-19 → 09-21 | `frank-large-ciru-orca.md` |
+| unsloth llama.cpp b11030 Qwen3.8-Flash-Next UD-IQ4_XS (`frank-large`) | Dankclaw | 2026-09-21 (same-day swap) | `frank-large-unsloth-qwen38-flash-next.md` |
 | ISTA-DASLab Qwen3.8-27B-GSQ-RCO IQ3_S (`frank-small`) | Dankclaw | 2026-09-16 → 09-17 | `frank-small-qwen38-gsq-rco.md` |
 | vLLM Gemma4-12B w4a16 (`frank-small`) | Dankclaw | 2026-09-19 (same-day revert) | `frank-small-vllm-gemma4.md` |
 | agentionai ROCmFP4-FAST imatrix | Dankclaw | 2026-08-29 → 08-30 | `agentionai-fast-imatrix.md` |

serverAppConfigs-docs/LLM/frank-large-kairic-edge-qwen38-27b.md

@@ -0,0 +1,195 @@
+---
+type: reference
+title: Kairic Edge Qwen3.8-27B IU4 (W4A4) on Dankclaw (frank-large)
+description: The active frank-large runbook — the Kairic Edge runtime (ciru-ai/ROCmFPX, branch kairic-edge-qwen38-27b-v1.2, commit 205a3e5) serving jcbtc/Qwen3.8-27B-IU4-Kairic-Edge (27B dense, IU4 W4A4) on the Dankclaw Strix Halo iGPU: the source-built runtime, the full-window/one-stream shape, the MTP depth 4 + n-gram spec method, the three PromptForge sidecars, the compatibility mode, the payload, the client contract, and the failure modes worth knowing.
+tags:
+  - llm
+  - kairic-edge
+  - rocmfpx
+  - dankclaw
+  - frank-large
+  - strix-halo
+  - gfx1151
+  - iu4
+  - w4a4
+  - rocm
+  - mtp
+  - promptforge
+timestamp: 2026-09-21
+---
+
+# Kairic Edge Qwen3.8-27B IU4 (W4A4) on Dankclaw (frank-large)
+
+> **ACTIVE since 2026-09-21.** It replaced the unsloth llama.cpp prebuilt
+> (b11030, Qwen3.8-Flash-Next UD-IQ4_XS, 125B MoE — see
+> [[frank-large-unsloth-qwen38-flash-next]], the current rollback target),
+> which had replaced the CIRU v4.4.1 Orca runtime (see
+> [[frank-large-ciru-orca]]). Deployed as a **root systemd unit**
+> (`scripts/frank-large.service`, `User=dank`), port 7770, on the same
+> gfx1151 iGPU. The RTX 3090 it does not touch belongs to
+> [[frank-small-gemma4-12b]].
+
+The model is `jcbtc/Qwen3.8-27B-IU4-Kairic-Edge` — a **27B dense** Qwen3.8
+at **IU4** (W4A4, integer-weights / integer-activations). It is a
+fundamentally different architecture from the 125B MoE it replaces: no
+PLE, no MoE experts, no n-gram embedding. The payload is four files: the
+15.5 GiB main GGUF plus three `.pfs` sidecars (FFN 7.99 GiB, GDN 1.88
+GiB, GDN-Output 0.70 GiB) — the PromptForge IU4 weight shards the Kairic
+Edge runtime loads alongside the main GGUF.
+
+The runtime is the **Kairic Edge** build of `ciru-ai/ROCmFPX` (branch
+`kairic-edge-qwen38-27b-v1.2`, commit `205a3e5`), built from source
+(`scripts/build-kairic-edge-gfx1151.sh`). It is a llama.cpp build with the
+PromptForge sidecar env block and the `--kairic-edge` qualified serving
+path.
+
+## Why this swap
+
+- The operator asked for the Kairic Edge 27B model at **one conversation,
+  full context (262,144)** (2026-09-21).
+- The Kairic Edge runtime is the qualified IU4 (W4A4) serving path — no
+  standard llama.cpp quant, no PLE sidecar payload, no QSA hotfix: one
+  GGUF, three sidecars, done.
+- The spec method is native MTP depth 4 + n-gram drafting (24/64/64).
+  DFlash is NOT available for this model (no `DRAFT_DFLASH` spec type in
+  the Kairic Edge runtime).
+
+## Shape
+
+One root unit, one process, one published port:
+
+| half | port | reachable |
+|---|---|---|
+| llama-server (OpenAI front-end + engine, single process) | 7770 | published as host **7770** |
+
+## Runtime
+
+- **Source build**: `scripts/build-kairic-edge-gfx1151.sh` (TheRock
+  7.15.0a20260718 toolchain, AMD clang 23.0.0, HIP 7.15.0, GCC 13.3.0,
+  CMake 4.4.2, Ninja 1.13.0). Output at
+  `/home/dank/GitPackages/ROCmFPX-kairic/build-kairic/bin/llama-server`.
+- **Composable Kernel**: `fdf4bb7fcc984811cef48ce817d89aac064b984a` +
+  `patches/composable-kernel-gfx1151-iu4.patch` (SHA-256
+  `ea57bca3793d35d884fc156b6c0bc33d8e672e3bb49f66ff67338503029d6af5`).
+  The CK `config.h` is generated by CMake's `configure_file` (line 334 of
+  CK's CMakeLists.txt) — it is untracked, so a `git clean` removes it.
+- **GPU target**: `gfx1151` (Strix Halo). The build takes ~4 minutes
+  (`JOBS=$(nproc)`).
+- **v1.2 changes**: Exact 65-row n-gram verification switched to the compact
+  authoritative path by default; the native IU4 M65 verifier is retained
+  only for diagnostics.
+
+## Spec method
+
+- **Native MTP depth 4** (`--spec-type draft-mtp --spec-draft-n-max 4`):
+  the model's MTP layers draft 4 tokens per step.
+- **N-gram drafting** (24/64/64): the `ngram-mod` matcher chains behind
+  the MTP drafter (the `--spec-type draft-mtp` value builds both).
+- **DFlash is NOT available**: the Kairic Edge runtime's spec-type
+  constants are `DRAFT_EAGLE`, `DRAFT_MTP`, `DRAFT_SIMPLE`,
+  `NGRAM_CACHE`, `NGRAM_MAP_K`, `NGRAM_MOD`, `NGRAM_SIMPLE`, `NONE` — no
+  `DRAFT_DFLASH`. The z-lab DFlash2-FP8 drafter (frank-medium's drafter)
+  cannot be used.
+- **Draft device**: `--spec-draft-device ROCm0 --spec-draft-ngl 999`
+  (the drafter runs on the iGPU, all layers).
+
+## Compatibility mode
+
+The Kairic Edge runtime has two modes:
+
+- **Fast-greedy** (`KAIRIC_EDGE_COMPATIBILITY_MODE=0`, the runner's
+  default): rejects request features that require full target logits,
+  including sampling, penalties, probabilities, grammar-constrained tool
+  calls, logit bias, LoRA, and a reasoning budget.
+- **Compatibility** (`KAIRIC_EDGE_COMPATIBILITY_MODE=1`): enables all of
+  the above (9.7% slower per the build guide).
+
+The harness (OMP) needs sampling, tools and a reasoning budget, so
+`COMPATIBILITY_MODE=1` is the deployed shape. In compatibility mode:
+`LLAMA_TARGET_GREEDY_ARGMAX_FASTPATH=0` and
+`PROMPTFORGE_OUTPUT_K8_STRICT_GREEDY=0`.
+
+**Known gotcha**: the greedy-argmax fastpath (fast mode) rejects
+non-greedy requests and reasoning budgets. Re-test chat before production
+if you flip to fast mode.
+
+## PromptForge sidecars
+
+The three `.pfs` sidecars are wired via the `PROMPTFORGE_*` env block
+(the certified runner's exact env):
+
+| sidecar | env var | size |
+|---|---|---|
+| FFN | `PROMPTFORGE_IU4_SIDECAR` / `PROMPTFORGE_SIDECAR` | 7.99 GiB |
+| GDN | `PROMPTFORGE_GDN_SIDECAR` | 1.88 GiB |
+| GDN-Output | `PROMPTFORGE_GDN_OUTPUT_SIDECAR` | 0.70 GiB |
+
+The serve script (`scripts/serve-frank-large.sh`) validates binary → main
+GGUF → 3 sidecars and exits with a pointer message if any is missing, then
+`exec`s `llama-server` with `--jinja --alias frank-large
+--chat-template-kwargs '{"preserve_thinking":true}'` (Qwen3.8's template
+needs this to carry thinking blocks across turns; a request-level value
+still wins).
+
+## Memory budget
+
+The iGPU addresses **114 GiB** (the GTT aperture over the shared LPDDR,
+`gtt_total` in `/sys/class/drm/card1/device/`; `rocm-smi`'s 2 GiB
+"dedicated" is not the budget). The 27B dense model (26 GiB total) is
+mmap'd in with `-ngl 999`; budget at 262k ≈ 30 GiB (weights + KV +
+buffers), leaving ~84 GiB of aperture headroom. The 8 GiB prompt-cache
+budget (`CACHE_RAM=8192`) is the Kairic Edge qualified config. The model
+is 27B dense (not DeltaNet), so the fleet's 12.8 GiB DeltaNet `CACHE_RAM`
+floor does not apply.
+
+## Payload
+
+`scripts/download-frank-large-kairic.sh` (resumable, each file verified
+against its declared byte count + sha256; `--verify-only` re-checks):
+
+| file | size | sha256 |
+|---|---|---|
+| `Qwen3.8-27B-IU4-Kairic-Edge.gguf` | 16,617,792,672 | `360caf73…` |
+| `Qwen3.8-27B-Kairic-IU4-FFN.pfs` | 8,576,856,064 | `adcbb90a…` |
+| `Qwen3.8-27B-Kairic-IU4-GDN.pfs` | 2,019,569,664 | `82f93131…` |
+| `Qwen3.8-27B-Kairic-IU4-GDN-Output.pfs` | 756,953,088 | `3b07e7b1…` |
+
+## Client contract
+
+- **Port**: 7770 (the same port and alias the unsloth predecessor served).
+- **Alias**: `frank-large`.
+- **Context**: 262,144 (the model's native window), 1 slot.
+- **Reasoning**: enabled (`--reasoning auto --reasoning-format deepseek
+  --reasoning-budget -1`), extracted to `reasoning_content`.
+- **Vision**: text-only (the model has no vision projector). The fleet's
+  image path is [[frank-small-gemma4-12b]] either way.
+- **Reasoning effort**: the Qwen3.8 template gates `reasoning_effort` to
+  {xhigh, medium, low} — the harness folds its levels onto that set in
+  `models.yml` (`reasoningEffortMap`).
+
+## Measured performance
+
+10-question conversation (2026-09-21, post-deploy): **23.99s total, 530
+tokens, 22.1 t/s average**. Per-question: 1.05–3.57s, 16.9–29.5 t/s. The
+MTP depth 4 + n-gram spec method is working (draft acceptance logged, both
+`ngram-mod` and `draft-mtp` active in the journal).
+
+## Failure modes worth knowing
+
+- **CK `config.h` is untracked**: a `git clean` in the CK checkout removes
+  it, and the next build fails. Re-run the build script (it re-checks-out
+  the CK commit and re-applies the patch).
+- **Fast-greedy mode rejects the harness**: if you flip to
+  `COMPATIBILITY_MODE=0`, the harness's sampling/tools/reasoning-budget
+  requests are rejected. Re-test chat before production.
+- **The `charlie12345` fork is NOT the Kairic Edge repo**: the local
+  clone at `/home/dank/GitPackages/ROCmFPX` is the `charlie12345/ROCmFPX`
+  fork (no kairic branch). The Kairic Edge build uses the `ciru` remote
+  (`https://github.com/ciru-ai/ROCmFPX.git`), branch
+  `kairic-edge-qwen38-27b-v1.2`, commit `205a3e5`, in the worktree at
+  `/home/dank/GitPackages/ROCmFPX-kairic/`.
+
+## Rollback
+
+[[frank-large-unsloth-qwen38-flash-next]] — the unsloth prebuilt payload
+and runtime are intact on disk.

serverAppConfigs-docs/LLM/index.md

@@ -4,10 +4,11 @@ Documentation for the LLM inference fleet on the two hosts (2026-09-21):
 **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 + the z-lab DFlash2 drafter, bf16 KV, TP=2 over the
-R4D one-shot allreduce), and TWO endpoints on Dankclaw — the unsloth
+R4D one-shot allreduce), and TWO endpoints on Dankclaw — the Kairic Edge
-llama.cpp prebuilt (frank-large, Qwen3.8-Flash-Next UD-IQ4_XS on the gfx1151
+runtime (frank-large, ciru-ai/ROCmFPX v1.2, jcbtc Qwen3.8-27B-IU4-Kairic-Edge
-iGPU, port 7770) and mainline llama.cpp (frank-small, HauhauCS Gemma4-12B QAT
+IU4 W4A4 on the gfx1151 iGPU, port 7770) and mainline llama.cpp (frank-small,
-Q4_K_M with MTP and vision on the RTX 3090, port 7771).
+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
@@ -31,10 +32,10 @@ ONE process on both cards, 262144 ctx, up to 8 seqs]
     subgraph Dankclaw[AMD Strix Halo - Ubuntu 26.04]
         E2[RTX 3090 (PCIe x4 dock) +
 gfx1151 iGPU 114 GiB GTT]
-        E[unsloth llama.cpp b11030 (ROCm gfx1151)
+        E[Kairic Edge (ciru-ai/ROCmFPX v1.2, gfx1151)
 frank-large, port 7770]
-        F[Qwen3.8-Flash-Next UD-IQ4_XS
+        F[Qwen3.8-27B-IU4-Kairic-Edge (IU4 W4A4)
-200000 ctx / 1 slot, MTP depth 2]
+262144 ctx / 1 slot, MTP depth 4 + n-gram]
         G[mainline llama.cpp 37b53fd
 frank-small, port 7771]
         H[Gemma4-12B QAT Q4_K_M
@@ -95,11 +96,18 @@ frank-small, port 7771]
   (bs1/bs3/bs4/bs6, 8k–700k KV) on Dankserver RTX 3090
 - [[deployment]] — deploy and update process for both servers
 - [[frank-redo-2026-08-17]] — the 2026-08-17 topology change
-- [[frank-large-unsloth-qwen38-flash-next]] — ACTIVE frank-large runbook
+- [[frank-large-kairic-edge-qwen38-27b]] — ACTIVE frank-large runbook
-  since 2026-09-21 (root systemd unit, port 7770): the unsloth llama.cpp
+  since 2026-09-21 (root systemd unit, port 7770): the Kairic Edge runtime
-  prebuilt (b11030-mix-5ff778e, ROCm gfx1151) serving
+  (ciru-ai/ROCmFPX v1.2, built from source) serving
-  unsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ4_XS on the gfx1151 iGPU — one
+  jcbtc/Qwen3.8-27B-IU4-Kairic-Edge (IU4 W4A4, 27B dense) on the gfx1151
-  200,000-token conversation, MTP depth 2 via the explicit -md shared-Q8_0
+  iGPU — one full 262,144-token conversation, MTP depth 4 + n-gram drafting,
+  the three PromptForge sidecars, compatibility mode, the 114 GiB GTT memory
+  model, client contract, troubleshooting
+- [[frank-large-unsloth-qwen38-flash-next]] — RETIRED 2026-09-21 (same-day
+  swap, replaced by [[frank-large-kairic-edge-qwen38-27b]]; rollback target):
+  the unsloth llama.cpp prebuilt (b11030-mix-5ff778e, ROCm gfx1151) serving
+  unsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ4_XS (125B MoE) on the gfx1151 iGPU —
+  one 200,000-token conversation, MTP depth 2 via the explicit -md shared-Q8_0
   head, the 114 GiB GTT memory model, client contract, troubleshooting
 - [[frank-large-ciru-orca]] — RETIRED 2026-09-21 (replaced by
   [[frank-large-unsloth-qwen38-flash-next]]; rollback target): the CIRU
@@ -167,7 +175,7 @@ frank-small, port 7771]
   (deployed and reverted 2026-08-22)
 - [[Dankserver System Specs]] — the 2x R9700 box (frank-medium)
 - [[Dankclaw System Specs]] — the Strix Halo gfx1151 box (frank-large on the
-  unsloth llama.cpp prebuilt since 2026-09-21, frank-small on the RTX 3090)
+  Kairic Edge runtime since 2026-09-21, frank-small on the RTX 3090)
 - [[frank-npu]] — RETIRED 2026-09-11: the FLM NPU sight+sound endpoint
   on Dankclaw (Gemma4 E4B vision+audio pack, XDNA2, port 7771), kept as
   the retirement record — the IOMMU/SVA err=-19 root cause and where

serverAppConfigs-docs/index.md

@@ -147,12 +147,19 @@ The LLM inference fleet on the two hosts. Full index:
   agentionai/Qwen3.8-Flash-Next-ROCmFP4-FAST-imatrix (87.06 GiB,
   Q4_0_ROCMFP4_FAST) + own MTP draft, build-qwen38 (retired 2026-08-30;
   rollback record)
-- [[frank-large-unsloth-qwen38-flash-next]] — the ACTIVE frank-large runbook
+- [[frank-large-kairic-edge-qwen38-27b]] — the ACTIVE frank-large runbook
-  since 2026-09-21 (root systemd unit, port 7770): the unsloth llama.cpp
+  since 2026-09-21 (root systemd unit, port 7770): the Kairic Edge
-  prebuilt (b11030-mix-5ff778e, ROCm gfx1151) serving
+  runtime (ciru-ai/ROCmFPX kairic-edge-qwen38-27b-v1.2, TheRock 7.15.0,
-  unsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ4_XS on the gfx1151 iGPU — one
+  Composable Kernel) serving jcbtc/Qwen3.8-27B-IU4-Kairic-Edge (a 27B
-  200,000-token conversation, MTP depth 2 via the explicit -md shared-Q8_0
+  dense model, main GGUF + FFN/GDN/GDN-Output .pfs sidecars) on the gfx1151
-  head, the 114 GiB GTT memory model, client contract
+  iGPU — one 262,144-token conversation, native MTP depth 4 + n-gram
+  drafting, compatibility mode, the 114 GiB GTT memory model, client contract
+- [[frank-large-unsloth-qwen38-flash-next]] — RETIRED 2026-09-21 (replaced by
+  [[frank-large-kairic-edge-qwen38-27b]]; same-day swap): the unsloth
+  llama.cpp prebuilt (b11030-mix-5ff778e, ROCm gfx1151) serving
+  unsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ4_XS (a 125B MoE / 6B active) on the
+  gfx1151 iGPU — one 200,000-token conversation, MTP depth 2 via the
+  explicit -md shared-Q8_0 head, the 114 GiB GTT memory model, client contract
 - [[frank-large-ciru-orca]] — RETIRED 2026-09-21 (replaced by
   [[frank-large-unsloth-qwen38-flash-next]]; rollback target, 2026-09-19 →
   09-21): the CIRU v4.4.1 runtime (private host build, QSA hotfix) serving