Skip to content

Pull requests: vllm-project/vllm-gaudi

New pull request New
50 Open 214 Closed
50 Open 214 Closed
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
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

[upstream crash] fix spec decode due to upstream 24986
#265 opened Sep 26, 2025 by xuechendi Loading…
Convert padding itertools.islice to list
#264 opened Sep 25, 2025 by malsbat Loading…
1
v0.10.2 [SW-236002] Enable group indexing for compressed w4a16 format (#243) - cherry-pick
#263 opened Sep 25, 2025 by skavulya Loading…
Enable modification of prompt BS
#258 opened Sep 25, 2025 by ksmusz Loading…
[SW-239237] Store stable vllm commit in VLLM_STABLE_COMMIT file
#257 opened Sep 25, 2025 by bmyrcha Loading…
@bmyrcha
Update long context README
#256 opened Sep 25, 2025 by iboiko-habana Loading…
1
Update LoRA tests
#255 opened Sep 25, 2025 by vivekgoe Loading…
enable p2d4
#253 opened Sep 24, 2025 by hsubramony • Draft
Add restriction of usage VLLM_DECODE_BLOCK_BUCKET_MAX>max_blocks
#245 opened Sep 24, 2025 by iboiko-habana Loading…
2
Support DP for unified attention
#242 opened Sep 24, 2025 by wuxun-zhang Loading…
4
Fix auto-merge, now even e2e_test failed, PR still can be auto-merged
#239 opened Sep 23, 2025 by xuechendi • Draft
Add assert for empty buckets
#236 opened Sep 23, 2025 by iboiko-habana Loading…
Enable H2d(runtime scale patching) for Torch compile by default
#235 opened Sep 23, 2025 by jczaja Loading…
4
[0.10.2] Fix calculating used blocks in unified attention
#234 opened Sep 23, 2025 by madamczyk-intel Loading…
Fix calculating used blocks in unified attn
#232 opened Sep 23, 2025 by madamczyk-intel Loading…
[Docs] README update - bucketing, warmup
#231 opened Sep 23, 2025 by adobrzyn Loading…
13
Enable modification of prompt BS
#224 opened Sep 22, 2025 by ksmusz Loading…
KV cache sharing
#223 opened Sep 22, 2025 by jakub-sochacki • Draft
Add tests for custom operator implementation correctness
#222 opened Sep 22, 2025 by Kacper-Pietkun • Draft
[DO NOT MERGE] Update README.md
#220 opened Sep 22, 2025 by kzawora-intel Loading…
Port: Adding prompt context flags for linear warmup
#218 opened Sep 22, 2025 by iboiko-habana Loading…
1
Adding prompt context flags for linear warmup
#217 opened Sep 22, 2025 by iboiko-habana Loading…
2
Use type strings to be compatible with python 3.10
#214 opened Sep 22, 2025 by madamczyk-intel Loading…
[SW-240630] Qwen3-30B-MoE: Flatten post-attn seqs and restore model o…
#212 opened Sep 20, 2025 by attafosu Loading…
Prevents 'HPUModelRunner' object has no attribute 'graphed_buckets'
#210 opened Sep 19, 2025 by MohitIntel Loading…
ProTip! Adding no:label will show everything without a label.