forked from vllm-project/vllm
-
Notifications
You must be signed in to change notification settings - Fork 134
Pull requests: HabanaAI/vllm-fork
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
add VLLM_ENGINE_PROFILER_SKIP_STEPS to the engine profiler
#2143
opened Nov 19, 2025 by
yangulei
Loading…
Enable the graph mode and add the full warmup logic for Deepseek OCR model
#2138
opened Nov 17, 2025 by
HeJunyan
Loading…
[DeepSeek R1] chunked prefill warmup with chunk size
#2135
opened Nov 14, 2025 by
jerrychenhf
Loading…
fea(readme): VLLM_PROMPT_SEQ_BUCKET_MAX value update
#2121
opened Nov 6, 2025 by
imangohari1
Loading…
3 tasks
Workaround for Assertion error when embedding with bge-m3 in lazy mode
#2093
opened Oct 28, 2025 by
slokesha
Loading…
fix bug that VLLM_SKIP_WARMUP=1 is not recognized in vision_bucket
#2036
opened Oct 15, 2025 by
yingjie-han
Loading…
Previous Next
ProTip!
Updated in the last three days: updated:>2025-11-18.