Frank 9d7643ec5d frank-default-small: ncmoe 35->36 for prefill stability ...

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.

2026-08-14 10:56:40 -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.ling.env

ling B-test: spec off (--spec-type none), keep parallel=2 - isolate spec path as freeze trigger

2026-08-14 03:39:15 -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: ncmoe 35->36 for prefill stability

2026-08-14 10:56:40 -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

frank-large-ling.service

dankclaw: Ling-3.0-flash Q6_K trial config (Vulkan+GTT+draft-mtp)

2026-08-14 01:20:30 -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-ling-flash.sh

ling: batch 8192 (ubatch 3072); add -lv verbosity + log file for stop-investigation

2026-08-14 02:12:35 -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: ncmoe 35->36 for prefill stability

2026-08-14 10:56:40 -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