Skip to content

Pull requests: vllm-project/vllm

New pull request New
478 Open 5,589 Closed
478 Open 5,589 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

[ROCm][V1] Add intial ROCm support to V1 ci/build v1
#12790 opened Feb 5, 2025 by SageMoore • Draft
2
[ROCm][Kernel] Using the correct warp_size value ready ONLY add when PR is ready to merge/full CI is needed
#12789 opened Feb 5, 2025 by gshtras Loading…
6
Update chat_utils.py to avoid issues when tool call is present but None frontend
#12788 opened Feb 5, 2025 by jgreer013 Loading…
1
[core][V1] pipeline parallel with threads needs-rebase v1
#12787 opened Feb 5, 2025 by ruisearch42 • Draft
2
Improve TransformersModel UX
#12785 opened Feb 5, 2025 by hmellor Loading…
2
[NVIDIA] Support nvfp4 quantization ci/build
#12784 opened Feb 5, 2025 by kaixih Loading…
1
[VLM] Update compatibility with transformers 4.49 documentation Improvements or additions to documentation ready ONLY add when PR is ready to merge/full CI is needed
#12781 opened Feb 5, 2025 by DarkLight1337 Loading…
5
[Hardware][Intel-Gaudi] Multi-step scheduling implementation for HPU
#12779 opened Feb 5, 2025 by tzielinski-habana Loading…
1
[Kernel] Make rotary_embedding ops more flexible with input shape ready ONLY add when PR is ready to merge/full CI is needed
#12777 opened Feb 5, 2025 by Isotr0py Loading…
2 tasks done
5
Use RMSNorm in TransformersModel ready ONLY add when PR is ready to merge/full CI is needed
#12776 opened Feb 5, 2025 by hmellor Loading…
11
[build][misc] allow to use recent numpy ci/build
#12759 opened Feb 5, 2025 by zhouyuan Loading…
1
7
[Misc] Update w2 scale loading for GTPQMarlinMoE
#12757 opened Feb 5, 2025 by dsikka • Draft
2
[Model][Speculative Decoding] DeepSeek MTP spec decode speculative-decoding
#12755 opened Feb 4, 2025 by luccafong Loading…
@LiuXiaoxuanPKU
24
[Frontend] Adding the "User Defined Custom Tool Calling" parser for the Llama models frontend
#12752 opened Feb 4, 2025 by lulmer Loading…
1
[WIP][v1][Metrics] Add design doc documentation Improvements or additions to documentation v1
#12745 opened Feb 4, 2025 by markmc • Draft
1
[Bugfix] Env var to to disable xgrammar any_whitespace needs-rebase structured-output
#12744 opened Feb 4, 2025 by wallashss Loading…
6
[Build] Do not add cmake/ninja dependencies when they are installed ci/build
#12739 opened Feb 4, 2025 by mgorny Loading…
1
Merge similar examples in offline_inference into single basic example documentation Improvements or additions to documentation
#12737 opened Feb 4, 2025 by hmellor Loading…
8
[Bugfix] Add Containerfile.arm for podman support
#12735 opened Feb 4, 2025 by kush-gupt Loading…
1
1
[Core] Add Additional Metrics to vLLM Server v1
#12726 opened Feb 4, 2025 by sahelib25 Loading…
19
[Bugfix] Fix disagg hang caused by the prefill and decode communication issues
#12723 opened Feb 4, 2025 by houseroad Loading…
1
Update to torch==2.6.0 ci/build ready ONLY add when PR is ready to merge/full CI is needed
#12721 opened Feb 4, 2025 by mgoin Loading…
1
6
[core] V1 pipeline parallel async execution loop needs-rebase v1
#12720 opened Feb 4, 2025 by ruisearch42 • Draft
2
[Model] Add support for partial rotary embeddings in Phi3 model
#12718 opened Feb 4, 2025 by garg-amit Loading…
1
Quantization and MoE configs for GH200 machines
#12717 opened Feb 4, 2025 by arvindsun Loading…
6
ProTip! Adding no:label will show everything without a label.