project6-dev cf4c16bb23 fix: copy_blocks use ixf_F.vllm_copy_cache directly

2026-08-13 00:56:21 +00:00

qwen3_6_scripts

fix: copy_blocks use ixf_F.vllm_copy_cache directly

2026-08-13 00:56:21 +00:00

.gitignore

feat: 13th .so topk_softmax + fp32 fix + max_completion_tokens

2026-08-12 16:13:13 +00:00

computility-run.yaml

fix: yaml params only — enforce_eager + dtype half + comp168 settings

2026-08-12 16:05:58 +00:00

Dockerfile

wudixzy stack docker build test: 2615-line qwen3_5.py + 12 prebuilt .so + 251-line patch_ops.sh

2026-08-12 03:17:31 +00:00

Description

No description provided

15 MiB

Languages

Python 88.5%

Cuda 9.2%

Shell 2.3%