Frank 6663af1041 Revert "Remove KV cache quantization, increase batch/ubatch on frank-default-large" ...

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.

2026-08-13 17:04:02 -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

docs+deploy: Dankserver now llama.cpp frank-default-small (HauhauCS Q6_K_P + DFlash)

2026-08-11 01:18:29 -07:00

frank-default-large.env

Revert "Remove KV cache quantization, increase batch/ubatch on frank-default-large"

2026-08-13 17:04:02 -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

Add recommended sampling defaults and reduce MoE GPU offload on dankserver

2026-08-13 16:18:47 -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

Revert "Remove KV cache quantization, increase batch/ubatch on frank-default-large"

2026-08-13 17:04:02 -07:00

serve-llama-frank-small.sh

Add recommended sampling defaults and reduce MoE GPU offload on dankserver

2026-08-13 16:18:47 -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