Skip to content

Pull requests: HabanaAI/vllm-fork

Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort

Pull requests list

remove token_types for non-rerank models
#1522 opened Jul 3, 2025 by gyou2021 Loading…
Fix proxy with right content type
#1519 opened Jul 3, 2025 by zhenwei-intel Loading…
add split qkv to gemma3
#1517 opened Jul 2, 2025 by skaulintel Loading…
Readme warmup update
#1512 opened Jul 2, 2025 by adobrzyn Loading…
Embedding fix: warmup failure in embedding model
#1510 opened Jul 2, 2025 by shepark Loading…
Rebase 0.9.0.1
#1507 opened Jul 1, 2025 by michalkuligowski Loading…
docker vllm: add new configs
#1506 opened Jul 1, 2025 by tthaddey Loading…
Add runtime FP8 conversion for gaudi2
#1505 opened Jul 1, 2025 by kwisniewski98 Loading…
Port high-level profiler to V1 engine
#1501 opened Jul 1, 2025 by jkaniecki Loading…
Fix structure output
#1494 opened Jun 30, 2025 by inkcherry Loading…
[DeepSeek R1] Initial torch.compile support
#1492 opened Jun 28, 2025 by xinyu-intel Loading…
Fix shutdown issue of inc during exit
#1487 opened Jun 27, 2025 by mengniwang95 Loading…
adding wpyszka to codeowners
#1480 opened Jun 25, 2025 by wpyszka Loading…
Remove sync point in warmup
#1472 opened Jun 24, 2025 by kzawora-intel Loading…
Enable vision bucketing/warmup for gemma3 model
#1470 opened Jun 23, 2025 by libinta Loading…
Sasarkar/jha/sliding window gemma3 1
#1460 opened Jun 23, 2025 by libinta Draft
Fix the script file typo in README file
#1458 opened Jun 22, 2025 by taotod Loading…
ProTip! Follow long discussions with comments:>50.