vllm/v1/worker/gpu_input_batch.py · 8ff4a9956693450a37843bde88934ebcea440402 · OpenDAS / vllm_cscc

[Async][Feat] support apply penalty or bad_words for async + spec (#30495) · 8ff4a995

zhrrr authored Jan 09, 2026


Signed-off-by: zhuhaoran <zhuhaoran.zhr@alibaba-inc.com>
Signed-off-by: izhuhaoran <izhuhaoran@qq.com>
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>

8ff4a995

gpu_input_batch.py 42.7 KB

Replace gpu_input_batch.py