- frank-default-large: GGML_CUDA_FA_ALL_QUANTS=ON is mandatory in the
FastMTP build; without it q8_0 KV + FA falls back to a slow path and
prefill collapses ~12x (95 -> 1312 t/s at 8K, measured)
- frank-default-small: FLASH_ATTENTION_TRITON_AMD_ENABLE=TRUE + pure-python
flash_attn (triton_amd) + stub; without it the vision encoder warmup
OOMs via torch SDPA
- MODEL_FILE -> Qwen3.8-27B-Uncensored-Q6_K.gguf (22.43 GB, no bundled
MTP head; repo ships a standalone draft sidecar)
- SPEC_DRAFT_MODEL -> Qwen3.8-27B-Uncensored-draft-Q8_0.gguf (3.16 GB)
- CACHE_TYPE_K=q8_0, CACHE_TYPE_V=f16 (mismatched, FA retained via the
GGML_CUDA_FA_ALL_QUANTS rebuild of head HIP + worker CUDA at 9b05354ec)
- Split kept at 0.53 for phase 1 (Q6_K frees ~4.7 GiB on the worker at
this split); re-maximize after measuring draft placement
- KV math: K 1088 B/token + V 2048 B/token = 784 MiB per FA layer
- FLM_MODEL=qwythos:9b, CTX 262144, turbo+asr kept
- Add FLM_CONFIG_PATH/FLM_XCLBIN_PATH: the custom tag lives in the user
registry (~/.config/flm/model_list.json) + user xclbins; without them
flm hits the unknown-tag fallback and serves llama3.2:1b silently
- Note FLM 0.9.45 -> 1.0.1 runtime upgrade (pack declares flm_version 1.0.0)
0.54 measured: weight boundary moved to 35 blocks but the KV-per-device
count (round(f x 66), independent of weight boundary) flipped to 9 FA ->
KV 9216 MiB -> OOM by ~740 MiB. The flip sits at f ~0.538, just below
the weight threshold for block 35 -> the 35-block config is unreachable.
0.53 gives 34 blocks (0-33), 8 FA, KV 8192 MiB under every rounding rule
(round/floor/ceil of 0.53x66 = 34.98 -> 34 or 35, never 36), predicted
~1.1 GiB free.
Single full-context slot instead of two half-context slots. The 3090 takes
~33 of 66 layers (up from 26): the VRAM budget frees up because the f16 KV
pool shrinks 401400 -> 262144. 33 layers is the max with a safety margin
(34 -> 244 MiB headroom, 35 -> OOM). Verified math: /tmp/vram-math.py from
live journal buffers.
Streaming requests with role=developer get HTTP 200 + error JSON as
first body; pi sees a chunkless stream. Fix: compat.supportsDeveloperRole
false on the model entry. Verified by field bisection + headless pi run.
- scripts: serve-pp-head/worker, envs, systemd units, pp-test.sh orchestrator, pp-bench.py
- head design verified in b10433 source + live 4B smoke test:
* no --device with --rpc (RPC device silently dropped otherwise)
* default device selection = [RPC0, ROCm0] (HIP registers before Vulkan)
* default split proportional to reported free mem = ~20/80 here, pin 1,1
* -dio required for large model over RPC
- docs: qwen3.8-strix-optimizations (ranked no-quant-downgrade levers,
quant landscape, 2026-08-16 test matrix), PP deployment runbook,
index updates, Dankclaw Improvements corrections (Vulkan0, no power_profile sysfs)
- worker built at 9b05354ec in /home/dank/llama-cpp-rpc worktree (CUDA+RPC)
- second head build build-vulkan-rpc (HIP off) for backend A/B
Recording the 54-config matrix, the realistic-prompt correction (n_max=5 not
10), the ubatch findings (256 is the safe/fast point), and the premature-stop
sampling-variance investigation.
Realistic-prompt tuning: n_max=5 peaks ~13.3 t/s (baseline 7.2). matrix used a
repetitive prompt that inflated MTP. n_max=10 is only ~8.6 t/s on real writing.
The f16/f16 KV pool costs 15640 MiB at 800768 cells. At full 800K the
3090 idled at 23966/24576 MiB and the 1472x1472 image warmup graph
failed cudaMalloc (needed +248 MiB). 700416 cells (175104/slot, 4 slots)
leaves ~2.3 GiB free after warmup. Parallel stays 4.
F16 K removes the flash-attn F16-conversion workspace (MMA_F16 prefill
kernel needs no copy when K is already f16). Trades static KV pool size
for the context-proportional workspace growth implicated in the
cublasSgemm_v2 crash class. VERBOSITY=4 run logs real allocation sizes;
refit CTX_SIZE if the pool does not fit on the 24 GiB 3090.
Fix a live crash: cuBLAS cudaErrorInvalidValue in ggml_cuda_mul_mat_cublas
killed the service during a 145k-token prefill burst at ncmoe35/ub3072.
ncmoe 36 moves one more expert layer to CPU: frees ~0.75 GiB peak VRAM
(grid: peak 8606 vs 9360 MiB at ub3072) for -2% prefill / -2% decode.
Keeps prefill priority (top ubatch tier). Docs synced; noted fallback
GGML_CUDA_FORCE_MMQ=1 if pressure persists.
Compiles the 5-subagent research fan-out (llama.cpp RPC, vLLM PP,
bandwidth math, mixed-vendor experiments, Qwen3.6-27B spec methods) into
the KB under docs/Pipeline Parallelism/ with an index, expected
performance estimates (1/2.5/10 GbE), and an EDUCATIONAL-ONLY two-node
Qwen3.6-27B Q8 split script set (MTP/DFlash/ngram-mod variants, DSpark
noted as vLLM-only). Nothing here is deployed or intended to run.
Prefill is the priority for this workload. Switch from decode-max
(ncmoe 32 / ubatch 1024) to prefill-max:
- n-cpu-moe 35, ubatch 3072: prefill ~1458 t/s (top tier), gen ~45.4 t/s,
~1.2 GiB headroom at the 800k pool.
- Gen is independent of ubatch; ub 3072 reaches best prefill with no
decode cost. Docs synced (benchmark Chosen State, deployment, specs).
Retest MTP at n_max 2 (vs 3) for the acceptance/speed tradeoff, keeping
MTP-alone + ubatch 8192. Re-benches gen t/s and re-runs the strict
parallel-safety test.
MTP+ngram benched 12.0-13.6 t/s (vs MTP alone 15.3-19.5) and is
parallel-safe, but slower - layering does not pay off. Back to MTP
alone. Test ubatch 8192 (== batch) using the VRAM headroom; watch for
OOM during load.
Test the MTP+ngram layering (ngram re-drafts on top of the MTP draft) at
ubatch 4096. Must clear the strict parallel-safety test and beat MTP
alone (15.3-19.5 t/s) to stay.
MTP (draft-mtp, n_max 3, a4lg MTP-ONLY-Q8_0) benches 15.3-19.5 t/s vs
ngram-mod 6.7-8.7 t/s and passes the strict LCP-reuse parallel test
(sim 0.996 / f_keep 0.994 launch while another slot generates - the
pattern that killed DFlash). ubatch 4096 to use the ~33 GiB VRAM
headroom; watch peak during load.
ngram-mod benchmark + parallel-safety test passed (A and B both survive
the LCP-reuse launch that killed DFlash). Now benching MTP sidecar
(a4lg/Qwen3.6-27B-MTP-ONLY-Q8_0.gguf, draft-mtp, n_max 3).
DFlash causes premature EOS on a generating slot when another task lands
with high LCP prompt reuse (shared draft ctx corruption, reproduced
2026-08-14 3x). Benching ngram-mod vs MTP sidecar to pick the
replacement. serve script now passes --spec-draft-model only for
draft-* spec types.
Cold loads after the cache drop measured 17 minutes on 2026-08-13, longer
than the previous 600s wait. HEALTH_WAIT[dankclaw]=600 iterations (20 min),
dankserver stays at 300 (10 min). AGENTS.md: update cold-load figure.
- deployment.md: document the sudoers NOPASSWD restart helpers on both
targets, the exact-argument matching quirk, and the 2026-08-13
'premature job release' investigation (server never preempts; aborts
were client-side; Dankserver crashed twice under researcher load).
- DFlash/DSpark doc: MTP requires MTP tensors in the target GGUF; the
HauhauCS Qwen3.6-27B GGUF has none (verified tensor listing); MTP-only
draft GGUFs (a4lg/lym00) pair via --spec-draft-model; flag rename
--spec-type mtp -> draft-mtp in b9180.
- AGENTS.md: operational quirks for the helpers, journal abort-vs-release
signature, and the Dankserver cublasSgemm crash signature.
The helper scripts (/usr/local/sbin/frank-restart-<large|small>.sh)
cover unit symlink, cache drop (dankclaw), daemon-reload, and restart
in one root-owned script, run via sudoers NOPASSWD. deploy.sh now uses
the helper when present and falls back to inline sudo commands.
- N_CPU_MOE 34→35: 5 expert layers on GPU instead of 6. Frees ~0.4-0.8 GiB
VRAM for OOM safety after high-load sessions OOM'd at 32 and 33.
- Sync stale doc references (deployment.md, Dankserver System Specs.md)
that still claimed 32/8; specs now estimate ~1.8 GiB headroom at 35.
Deterministic deployment instead of agent ritual:
- DROP_CACHES per target (dankclaw=1): runs 'sync; echo 3 >
/proc/sys/vm/drop_caches' before systemctl restart. Without it the
model load stalls at 28 GiB VRAM when the model pages are cached.
- FRANK_SUDO_PW env var: remote sudo pipes it via 'sudo -S' so the
script runs headless. Falls back to plain sudo otherwise.
- Health check runs curl on the target over ssh (127.0.0.1:7770 was
previously checked from the workstation, which can never see it).
Empirically verified on 2026-08-13 (caches dropped): batch 8192 / ubatch
2048 loads and serves at ctx 602100 with 61 GiB VRAM peak. The benchmark
doc's 'ubatch 2048 OOMs' results were confounded by page-cache pressure -
with the model's pages fully cached the KV/graph allocation stalls at
28 GiB VRAM. Drop caches (sync; echo 3 > /proc/sys/vm/drop_caches) before
starting a load to make restarts reliable.
The ROCm HIP runtime (libamdhip64) reads the TEMP environment variable as
its JIT kernel-cache temp directory. Commit db3eb01 added TEMP=1.0 to the
env files as a sampling default; the serve scripts export it via set -a.
HIP then used the path "1.0" for its cache, failed, and segfaulted with a
NULL-refcount unref (offset 0x446153 in libamdhip64) during model tensor
upload (ggml_backend_cuda_buffer_set_tensor). This crashed frank-default-
large on every restart from Aug 13 16:22 onward; the earlier c984a3e
"fix" (KV/batch changes) was unrelated.
Rename the sampling variable TEMP -> TEMPERATURE in both env files and
serve scripts. llama-server still receives --temp from the renamed var, so
sampling defaults are unchanged. The HIP runtime no longer sees a bogus
TEMP value. Affects frank-default-large (dankclaw) and frank-default-small
(dankserver).
The Aug 13 change crashed frank-default-large in a restart loop. The service
segfaulted ~15s into model load (SIGSEGV in hipMalloc during load). The
benchmark (frank-default-large-benchmark.md) already proved ubatch 2048 OOMs
(40.9GB prefill buffer) and batch 2048 / ubatch 512 is the fits-and-loads
config on the 96GiB UMA budget. Restore q8_0/q8_0 KV cache (FA pairing) and
batch 2048 / ubatch 512.
Also fix deployment.md: KV is q8_0 K / q8_0 V (not f16 V) since 334b6af.
- Remove CACHE_TYPE_K/CACHE_TYPE_V (fp16 default on GPU)
- Increase BATCH_SIZE from 2048 to 8192
- Increase UBATCH_SIZE from 512 to 2048
- Remove --cache-type-k and --cache-type-v from llama-server flags
- frank-default-large: add TEMP=1.0, TOP_K=20, TOP_P=0.95, MIN_P=0.0
(per HauhauCS Qwen3.6-27B model card, thinking-general mode)
- frank-default-small: add same sampling defaults
(per HauhauCS Qwen3.6-35B-A3B model card)
- frank-default-small: reduce N_CPU_MOE from 33 to 34 (6 expert
layers on GPU instead of 7) to prevent OOM during high-load sessions
- Both serve scripts pass --temp, --top-k, --top-p, --min-p to
llama-server; clients can still override per-request via API
Root cause of ~1 t/s long-context decode: llama.cpp build has
GGML_CUDA_FA_ALL_QUANTS=OFF, and FA requires K type == V type.
Mixed cache q8_0/f16 silently disabled FA, collapsing decode at
200k ctx. Set V to q8_0 (halves V memory too) and retune
threads 12/1 for 16 Zen5 cores.
Frank