Skip to content

Pull requests: HabanaAI/vllm-fork

New pull request New
48 Open 2,090 Closed
48 Open 2,090 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

[aice/v1.22.0][WIP] add bf16 step3p5 on gaudi
#2244 opened Mar 11, 2026 by ranzhejiang Loading…
[aice/v1.22.0][WIP] Enable step3p5
#2243 opened Mar 10, 2026 by ranzhejiang • Draft
Bump xgrammar from 0.1.19 to 0.1.32 in /requirements dependencies Pull requests that update a dependency file python Pull requests that update python code
#2241 opened Mar 5, 2026 by dependabot bot Loading…
Bump actions/stale from 9.1.0 to 10.2.0 dependencies Pull requests that update a dependency file github_actions Pull requests that update GitHub Actions code
#2235 opened Feb 23, 2026 by dependabot bot Loading…
Qwen3.5
#2234 opened Feb 12, 2026 by wenbinc-Bin Loading…
Reduce the host overhead of Minimax-M2
#2228 opened Feb 3, 2026 by yangulei Loading…
2
Port hunyuan ocr model to Gaudi
#2213 opened Jan 8, 2026 by HeJunyan Loading…
5
Enable fp32 softmax for qwen 7b models
#2210 opened Jan 6, 2026 by yangulei Loading…
1
Fix the error of using the wrong model name in the document.
#2208 opened Dec 29, 2025 by wenbinc-Bin Loading…
1
Fix AttributeError in fixed_sub_image_list for embedding models
#2206 opened Dec 24, 2025 by majunpo Loading…
Multi-modal disaggregation for gemma, POC
#2205 opened Dec 23, 2025 by splotnikv • Draft
3 tasks
Update cli_args.py stale
#2189 opened Dec 17, 2025 by michalkuligowski Loading…
1
Enabled DeepSeek-Eagle on VLLM V0 for Gaudi stale
#2184 opened Dec 15, 2025 by gyou2021 Loading…
2
Delay prefix cache calculation to find longest common prefix stale
#2170 opened Dec 8, 2025 by ikurtchen Loading…
3 tasks done
2
Enable delayed sampling for warmup also to remove graph compilation i… stale
#2164 opened Dec 4, 2025 by yeonsily Loading…
3 tasks
1
Libint/add topk sampling scalar padding stale
#2160 opened Dec 1, 2025 by libinta Loading…
3 tasks
1
fix bs>1 crash issue for ovis stale
#2158 opened Dec 1, 2025 by libinta Loading…
3 tasks
1
add VLLM_ENGINE_PROFILER_SKIP_STEPS to the engine profiler stale
#2143 opened Nov 19, 2025 by yangulei Loading…
2
refactor(hpu_model_runner): restructure multimodal-related code
#2066 opened Oct 22, 2025 by Jing1Ling • Draft
3 tasks
2
Slokesha port ovis
#2063 opened Oct 21, 2025 by slokesha • Draft
3 tasks
Porting_ovis
#2044 opened Oct 16, 2025 by SupreetSinghPalne • Draft
3 tasks
Spalne/porting ovis
#2038 opened Oct 16, 2025 by SupreetSinghPalne • Draft
3 tasks
Fix cache miss for Ovis2.5
#2035 opened Oct 15, 2025 by Jianhong-Zhang • Draft
1
Fix cache miss for InternVL
#2034 opened Oct 15, 2025 by Jianhong-Zhang • Draft
Keep grids tensor on CPU in multimodal kwargs
#2019 opened Oct 10, 2025 by slokesha • Draft
3 tasks
ProTip! Filter pull requests by the default branch with base:habana_main.