Frank a27839519e dankclaw: FINAL spec - draft-mtp n_max 3, ubatch 8192 ...

n_max 2 benched 12.4-14.3 t/s (slower than n_max 3 at 15.3-19.5);
n_max 3 is the MTP sweet spot. ubatch 8192 (==batch) uses the VRAM
headroom (65.5 GiB of 96 GiB) safely. MTP beats ngram-mod (~7 t/s) and
matches DFlash (~20 t/s) without the parallel premature-EOS bug.

2026-08-13 23:07:38 -07:00

..

bench-frank-large.sh

feat: frank-default-large → llama.cpp Qwen3.6-27B Q8_K_P + DFlash draft + ngram-mod (bench pending)

2026-08-11 13:47:37 -07:00

bench-pipeline-64k.sh

bench: 4k pipeline harness w/ early crash check; parametrized spec-type

2026-08-11 16:14:44 -07:00

deploy.sh

deploy.sh: per-target health wait; 20 min for Dankclaw cold loads

2026-08-13 21:01:01 -07:00

frank-default-large.env

dankclaw: FINAL spec - draft-mtp n_max 3, ubatch 8192

2026-08-13 23:07:38 -07:00

frank-default-large.service

feat: frank-default-large → llama.cpp Qwen3.6-27B Q8_K_P + DFlash draft + ngram-mod (bench pending)

2026-08-11 13:47:37 -07:00

frank-default-small.env

frank-default-small: prefill-max ncmoe 35 / ubatch 3072

2026-08-13 23:07:30 -07:00

frank-default-small.service

feat: frank-default-small = HauhauCS Qwen3.6-35B-A3B uncensored Q6_K_P + DFlash on dankserver

2026-08-11 00:57:04 -07:00

llama-server.service

sync scripts from remotes: ROCmFPX llama-server.service (dankclaw), dankserver vLLM serve/validate; drop failed-attempt scripts

2026-08-10 19:48:46 -07:00

serve-ling3-vllm.sh

feat: raise Ling-3 GPU memory utilization to 0.95

2026-08-10 23:25:02 -07:00

serve-llama-frank-large.sh

dankclaw: bench cycle 1 - switch spec to ngram-mod; draft flags conditional

2026-08-13 21:16:32 -07:00

serve-llama-frank-small.sh

frank-default-small: prefill-max ncmoe 35 / ubatch 3072

2026-08-13 23:07:30 -07:00

serve-vllm-qwen36-dflash.sh

sync scripts from remotes: ROCmFPX llama-server.service (dankclaw), dankserver vLLM serve/validate; drop failed-attempt scripts

2026-08-10 19:48:46 -07:00

validate-vllm.sh

sync scripts from remotes: ROCmFPX llama-server.service (dankclaw), dankserver vLLM serve/validate; drop failed-attempt scripts

2026-08-10 19:48:46 -07:00