Skip to content

Pull requests: vllm-project/vllm-gaudi

New pull request New
70 Open 475 Closed
70 Open 475 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

Draft: Prepare Unified Attention biases on HPU
#550 opened Nov 7, 2025 by kzawora-intel • Draft
13
Doc changes from main to 0.10.2 documentation Improvements or additions to documentation skip-gaudi-tests
#549 opened Nov 7, 2025 by mhelf-intel Loading…
2
Bulk docs to 0.11.0 documentation Improvements or additions to documentation skip-gaudi-tests
#547 opened Nov 7, 2025 by PatrykWo Loading…
1
[FIX_FOR_VLLM_LATEST] Fix upstream execute_model crash
#546 opened Nov 7, 2025 by iboiko-habana Loading…
9
[Docs] Readme for bucketing from file + env var added documentation Improvements or additions to documentation skip-gaudi-tests
#545 opened Nov 7, 2025 by adobrzyn Loading…
@mhelf-intel
9
Refactor part of spec decode structure identical to vLLM
#544 opened Nov 7, 2025 by jerrychenhf Loading…
4
Michalkuligowski patch 7
#542 opened Nov 6, 2025 by michalkuligowski • Draft
4
UX fix: hide warmup logs
#539 opened Nov 6, 2025 by adobrzyn Loading…
11
[SW-228042] Add support for dynamic vLLM kv-cache quantization
#538 opened Nov 6, 2025 by dudilester Loading…
4
[FIX_FOR_VLLM_LATEST] Fix cpu disable shared_experts VLLM_DISABLE_SHARED_EXPERTS_STREAM
#537 opened Nov 6, 2025 by pawel-olejniczak Loading…
1
[FIX_FOR_VLLM_LATEST] Fix 'HPUCompressedTensorsWNA16MoEMethod' object has no attribute 'fused_experts'
#535 opened Nov 6, 2025 by pawel-olejniczak Loading…
1
Updating data for the release 0.10.2 skip-gaudi-tests
#531 opened Nov 5, 2025 by PatrykWo • Draft
6
[Attention Metadata Overhaul 2/N] Move metadata processing outside HPUModelAdapter, prepare biases on CPU
#530 opened Nov 5, 2025 by kzawora-intel Loading…
16
[FIX_FOR_VLLM_LATEST] Fix upstream crash
#527 opened Nov 5, 2025 by iboiko-habana Loading…
10
[Attention Metadata Overhaul 1/N] Extract metadata update to HPUAttentionMetadataProcessor
#526 opened Nov 5, 2025 by kzawora-intel Loading…
9
enable lmcache
#521 opened Nov 5, 2025 by hsubramony Loading…
2
[FIX_FOR_VLLM_LATEST] fix scheduler
#520 opened Nov 4, 2025 by iboiko-habana Loading…
2
reduce graph recompilations in input embeddings for Gemma3
#519 opened Nov 4, 2025 by skaulintel • Draft
5
Add docker cmdline options to handle long context
#515 opened Nov 4, 2025 by nngokhale • Draft
4
[FIX_FOR_VLLM_LATEST] Apply fix for [Core] Async scheduling + structured outputs compatibility #26866
#512 opened Nov 3, 2025 by iboiko-habana Loading…
4
Call shutdown_inc to mitiagate driver worker teardown order
#511 opened Nov 3, 2025 by michalkuligowski • Draft
1
[FIX_FOR_VLLM_LATEST] Hourly 775 fix: 'HPUWorker' object has no attribute 'get_kv_connector…
#510 opened Nov 3, 2025 by pawel-olejniczak Loading…
[SW-243111] Add correctors for decode buckets
#509 opened Oct 31, 2025 by jbyczkow Loading…
1
Udpate TESTOWNERS
#495 opened Oct 28, 2025 by jbyczkow Loading…
4
Initial Commit GPT-OSS
#485 opened Oct 28, 2025 by hlahkar Loading…
1
ProTip! Add no:assignee to see everything that’s not assigned.