Skip to content

Pull requests: HabanaAI/vllm-fork

New pull request New
90 Open 1,631 Closed
90 Open 1,631 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

Refactor bias weights processing for custom fused MoE and update hpu ext commit
#1816 opened Aug 25, 2025 by ck-intel Loading…
Docker readme fixes 1.22
#1815 opened Aug 25, 2025 by PatrykWo Loading…
1
Fix bug when video input for qwen2_5_vl
#1812 opened Aug 25, 2025 by yingjie-han Loading…
1
Enable FSDPA Impl (prefill) in GPTOSS
#1811 opened Aug 25, 2025 by SKRohit Loading…
gemma3: move decode embedding from mm to gemma3 model
#1810 opened Aug 25, 2025 by libinta Loading…
4 tasks
[deepseek_r1] supppot "/v1/models" in proxy server
#1808 opened Aug 25, 2025 by ccrhx4 Loading…
1
Qwen2 5 vl no alignment
#1807 opened Aug 22, 2025 by malkomes Loading…
3 tasks done
2
[SW-232910] Poor TTFT troubleshooting tip
#1803 opened Aug 22, 2025 by michalkuligowski Loading…
1
Option to skip prefill sampling
#1802 opened Aug 22, 2025 by jerrychenhf Loading…
[SW-232910] Poor TTFT troubleshooting tip
#1801 opened Aug 22, 2025 by michalkuligowski Loading…
2
Bump transformers from 4.52.4 to 4.53.0 in /.jenkins dependencies Pull requests that update a dependency file python Pull requests that update python code
#1800 opened Aug 22, 2025 by dependabot bot Loading…
Fix the warmup issue of Deepseek MTP
#1792 opened Aug 21, 2025 by YuJiankang Loading…
1
[deepseek_r1]update decode benchmark code to generate N prompts.
#1789 opened Aug 21, 2025 by ccrhx4 Loading…
V1.22.0 next qwen2 5 vl no alignment
#1788 opened Aug 20, 2025 by malkomes • Draft
enable pin memeory for hpu
#1787 opened Aug 20, 2025 by libinta Loading…
3 tasks
Sampler output transfer from prefill to decode
#1785 opened Aug 20, 2025 by jerrychenhf Loading…
TP parallel seq_len for Gemma3
#1775 opened Aug 19, 2025 by Jianhong-Zhang • Draft
3
Update HPU prefill/prompt Attn usage for gptoss
#1770 opened Aug 18, 2025 by SKRohit Loading…
Bump actions/checkout from 4 to 5 dependencies Pull requests that update a dependency file github_actions Pull requests that update GitHub Actions code
#1767 opened Aug 18, 2025 by dependabot bot Loading…
2
Increase regional compilation multiplier
#1758 opened Aug 13, 2025 by mfylcek Loading…
4
parallel compile for fast warm up
#1750 opened Aug 13, 2025 by inkcherry Loading…
2
Support MLA for nixl_connector
#1749 opened Aug 12, 2025 by srajabos Loading…
3 tasks
Disallow output from prefill for non stream case
#1745 opened Aug 12, 2025 by jerrychenhf Loading…
Warmup support for async KV transfer
#1743 opened Aug 12, 2025 by jerrychenhf Loading…
disable select_token_indices adjust for decode
#1736 opened Aug 11, 2025 by xuechendi • Draft
1 of 4 tasks
ProTip! Find all pull requests that aren't related to any open issues with -linked:issue.