Frank 6bdabfc65b Add VLLM_USE_V2_MODEL_RUNNER=0 to skip V2 model runner MARLIN repacking OOM

2026-08-09 21:49:25 -07:00

..

llama-server.service

Bump context to 600000 (200000/stream x 3 parallel)

2026-08-07 17:18:10 -07:00

serve-llamacpp-dflash.sh

Bump context to 600000 (200000/stream x 3 parallel)

2026-08-07 17:18:10 -07:00

serve-vllm-qwen36-dflash.sh

feat: initial vLLM Qwen3.6-35B-A3B-FP8 serve script with DFlash drafting on dankserver

2026-08-07 18:28:38 -07:00

validate-vllm.sh

Update validation script to test parallel streams (4 concurrent requests)

2026-08-08 00:30:08 -07:00

validate.sh

Use --alias frank-default-large, multi-stream validation script

2026-08-07 17:15:09 -07:00

vllm-awq-qwen36-dflash-ampere.sh

Add VLLM_USE_V2_MODEL_RUNNER=0 to skip V2 model runner MARLIN repacking OOM

2026-08-09 21:49:25 -07:00

vllm-qwen36.service

feat: initial vLLM Qwen3.6-35B-A3B-FP8 serve script with DFlash drafting on dankserver

2026-08-07 18:28:38 -07:00