Skip to content

Pull requests: vllm-project/vllm-gaudi

New pull request New
73 Open 702 Closed
73 Open 702 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

Set device according to local rank
#788 opened Jan 8, 2026 by yangulei Loading…
10
Enable HPU Fused SDPA for Qwen3-VL vision attention using attention masks
#787 opened Jan 7, 2026 by slokesha Loading…
5
Draft: Add FlashAttention online merge in Unified Attention
#785 opened Jan 7, 2026 by kzawora-intel • Draft
5
[WIP] Add Chunked Shared Attention with Dense Biases
#784 opened Jan 7, 2026 by kzawora-intel • Draft
10
Revert "[GAUDISW-244336] Add missing long ctx prompt buckets (#739)"
#783 opened Jan 7, 2026 by wpyszka Loading…
1
Migrate INCConfig for HPU
#779 opened Jan 6, 2026 by yiliu30 Loading…
@xuechendi
7
lmcache ci test
#778 opened Jan 6, 2026 by hsubramony Loading…
@xuechendi
1
Implement profile_run method in HPU model runner
#775 opened Jan 4, 2026 by xwu-intel Loading…
15
[FIX_FOR_VLLM_LATEST] Fix embedding models, after bug found in #27614
#774 opened Jan 2, 2026 by iboiko-habana Loading…
2
Documentation: Fix the mobile navigation issue in v.0.13.0 documentation Improvements or additions to documentation skip-gaudi-tests
#772 opened Jan 2, 2026 by mhelf-intel Loading…
2
GPT OSS Integration Code
#771 opened Jan 2, 2026 by hlahkar Loading…
2
[GAUDISW-245117] add b2b matmul
#770 opened Jan 1, 2026 by linoybu Loading…
9
Upgrade transformers>= 4.56.0, <5
#767 opened Dec 30, 2025 by iboiko-habana Loading…
2
test - do not merge
#765 opened Dec 29, 2025 by nirda7 Loading…
3
Introduce absolute and relative padding limits to the linear bucketing
#762 opened Dec 26, 2025 by yangulei Loading…
21
fix empty buckets issue for enforce eager mode
#761 opened Dec 25, 2025 by yangulei Loading…
2
[GAUDISW-243560] Monkey-patching _get_attn_scale for the Llama4Attention layer
#760 opened Dec 24, 2025 by rsmyrek Loading…
2
multimodal model embedding fixes
#759 opened Dec 23, 2025 by libinta Loading…
3
debug inc
#755 opened Dec 23, 2025 by HolyFalafel • Draft
7
Prefill batching logic to handle chunked prefill/prefix caching for HPU
#753 opened Dec 23, 2025 by hlin99 Loading…
@kzawora-intel
4
Release Notes for v0.13.0 documentation Improvements or additions to documentation skip-gaudi-tests
#750 opened Dec 22, 2025 by mhelf-intel Loading…
1
[GAUDISW-244752] add dynamic scale for V-Cache on Hiddden dim
#749 opened Dec 21, 2025 by dudilester Loading…
16
Fix async_scheduling + batched prefill
#741 opened Dec 18, 2025 by tianmu-li Loading…
4
Added Qwen3 Test
#736 opened Dec 18, 2025 by slokesha Loading…
Dryrun implementation for generating command line file
#723 opened Dec 16, 2025 by rajanintel24 Loading…
12
ProTip! Follow long discussions with comments:>50.