Skip to content

Pull requests: vllm-project/vllm

New pull request New
381 Open 4,531 Closed
381 Open 4,531 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
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

[doc] format fix documentation Improvements or additions to documentation
#10789 opened Nov 30, 2024 by wangxiyuan Loading…
1
[Hardware][CPU] Refactor CPU vector types for ISAs
#10787 opened Nov 30, 2024 by ShawnD200 Loading…
1
feat(guided): xgrammar support ci/build documentation Improvements or additions to documentation
#10785 opened Nov 29, 2024 by aarnphm Loading…
1
[Bugfix] Multiple fixes to tool streaming when using auto tool choice. frontend
#10782 opened Nov 29, 2024 by cedonley Loading…
1
3
[Model]: add some tests for aria model
#10770 opened Nov 29, 2024 by xffxff • Draft
@Isotr0py
1
[Model] Replace embedding models with pooling adapter ci/build documentation Improvements or additions to documentation ready ONLY add when PR is ready to merge/full CI is needed
#10769 opened Nov 29, 2024 by DarkLight1337 Loading…
10
[Platform] Move async output check to platform
#10768 opened Nov 29, 2024 by wangxiyuan Loading…
5
Drop ROCm load format check
#10767 opened Nov 29, 2024 by wangxiyuan Loading…
3
[feature]：upstream quark format to vllm needs-rebase
#10765 opened Nov 29, 2024 by kewang-xlnx Loading…
2
[Misc] Improve type annotations for support_torch_compile ready ONLY add when PR is ready to merge/full CI is needed
#10763 opened Nov 29, 2024 by DarkLight1337 Loading…
1
support download Lora Model from ModelScope and download private mode…
#10762 opened Nov 29, 2024 by AlphaINF Loading…
6
[Bugfix] Prevent benchmark_throughput.py from using duplicated random prompts
#10753 opened Nov 28, 2024 by mgoin Loading…
2
Configuration of the model parallelism does not make sense
#10749 opened Nov 28, 2024 by fajavadi Loading…
1
[Misc][XPU] Avoid torch compile for XPU platform ci/build
#10747 opened Nov 28, 2024 by yma11 Loading…
2
[Model] Add elementwise_affine to RMSNorm and re-enable weights loading tracker for Mamba
#10739 opened Nov 28, 2024 by Isotr0py Loading…
2
[doc]Update config docstring
#10732 opened Nov 28, 2024 by wangxiyuan Loading…
6
[Core] Refactoring disaggregated prefilling/decoding using Mooncake Transfer Engine ci/build documentation Improvements or additions to documentation frontend
#10728 opened Nov 28, 2024 by alogfans Loading…
4
[WIP][V1] Ray executor
#10725 opened Nov 27, 2024 by rkooo567 Loading…
2
[Bugfix] Fix BNB loader target_modules
#10720 opened Nov 27, 2024 by jeejeelee Loading…
2
[Model] Support Mantis(LLaVA) model ci/build documentation Improvements or additions to documentation needs-rebase
#10711 opened Nov 27, 2024 by DarkLight1337 • Draft
1
2
[WIP][CI]add genai-perf benchmark in nightly benchmark ci/build
#10704 opened Nov 27, 2024 by jikunshang Loading…
1
[V1] Initial support of multimodal models for V1 re-arch
#10699 opened Nov 27, 2024 by ywang96 • Draft
1 of 4 tasks
@DarkLight1337
1
[WIP] Adding min tokens/repetition/presence/frequence penalties to V1 sampler
#10681 opened Nov 26, 2024 by sroy745 • Draft
1
[3/N] Support and implement merged input processor for LLaVA model ready ONLY add when PR is ready to merge/full CI is needed
#10676 opened Nov 26, 2024 by DarkLight1337 Loading…
8
[Doc] Add github links for source code references documentation Improvements or additions to documentation
#10672 opened Nov 26, 2024 by russellb Loading…
5
ProTip! Find all pull requests that aren't related to any open issues with -linked:issue.