Skip to content

Pull requests: vllm-project/vllm

New pull request New
542 Open 7,257 Closed
542 Open 7,257 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

[TPU][V1][DEBUG] Provide Env Variable To Disable Sampler ready ONLY add when PR is ready to merge/full CI is needed tpu Related to Google TPUs v1
#16063 opened Apr 4, 2025 by NickLucche Loading…
1
[ROCm][V1] Changes needed for making vllm run on Fedora 41 with gtx1100 ci/build
#16062 opened Apr 4, 2025 by martinhoyer Loading…
3
[Kernel] Support merge attn cuda kernel ci/build v1
#16060 opened Apr 4, 2025 by ywq880611 Loading…
1
[Bugfix][TPU] Fix V1 TPU worker for sliding window tpu Related to Google TPUs v1
#16059 opened Apr 4, 2025 by mgoin Loading…
1
[Bugfix] Fix default behavior/fallback for pp in v1 bug Something isn't working ready ONLY add when PR is ready to merge/full CI is needed v1
#16057 opened Apr 4, 2025 by mgoin Loading…
2
[fix]: Dockerfile.ppc64le fixes for opencv-python and hf-xet ci/build
#16048 opened Apr 4, 2025 by Shafi-Hussain • Draft
1
fix neuron config override
#16045 opened Apr 4, 2025 by ajayvohra2005 Loading…
2
[Misc] improve chat_with_tools example documentation Improvements or additions to documentation
#16044 opened Apr 4, 2025 by reidliu41 Loading…
1
Add NeuronxDistributedInference support, Speculative Decoding, Dynamic on-device sampling ci/build documentation Improvements or additions to documentation
#16043 opened Apr 4, 2025 by aws-satyajith Loading…
1
[CI/Build] Set up performance benchmark on TPUs ci/build
#16042 opened Apr 4, 2025 by yarongmu-google Loading…
1
[Bugfix] LoRA : Fix the order in which the kernels process LoRAs
#16040 opened Apr 3, 2025 by varun-sundar-rabindranath Loading…
1
1
Use moe_wna16 kernel for compressed tensors wna16 moe models
#16038 opened Apr 3, 2025 by mgoin Loading…
1
s390x: Fix PyArrow build and add CPU test script for Buildkite CI ci/build
#16036 opened Apr 3, 2025 by Nash-123 • Draft
3
[V1][Spec Decode] Eagle Model loading documentation Improvements or additions to documentation v1
#16035 opened Apr 3, 2025 by LiuXiaoxuanPKU Loading…
4
[ROCM] Add gfx950 to the custom attention archs
#16034 opened Apr 3, 2025 by jpvillam-amd Loading…
1
[NVIDIA] Support Cutlass MLA for Blackwell GPUs ci/build
#16032 opened Apr 3, 2025 by kaixih Loading…
1
Make fp8 quant respect fused modules mapping
#16031 opened Apr 3, 2025 by mgoin Loading…
1
[Misc] Auto detect bitsandbytes pre-quantized models documentation Improvements or additions to documentation quantization ready ONLY add when PR is ready to merge/full CI is needed
#16027 opened Apr 3, 2025 by tristanleclercq Loading…
1
3
[Doc][Bugfix] Add missing EOF in k8s deploy doc documentation Improvements or additions to documentation
#16025 opened Apr 3, 2025 by psschwei Loading…
1
[Benchmark] Add sampling parameters to benchmark_serving.
#16022 opened Apr 3, 2025 by hyeygit Loading…
10
[Feature] add model aware kv ops helper
#16020 opened Apr 3, 2025 by billishyahao Loading…
5
[Misc][Benchmark] Remove colon from key 'request_goodput:'
#16018 opened Apr 3, 2025 by appleparan Loading…
1
[Model] Add smolvlm support documentation Improvements or additions to documentation frontend v1
#16017 opened Apr 3, 2025 by chaunceyjiang Loading…
1
4
[Model] Add SupportsMultiModal.get_language_model interface tpu Related to Google TPUs v1
#16007 opened Apr 3, 2025 by NickLucche Loading…
8
[Misc] Fix test_sharded_state_loader.py(#16004)
#16005 opened Apr 3, 2025 by Accelerator1996 Loading…
1
ProTip! Adding no:label will show everything without a label.