Skip to content

Pull requests: vllm-project/vllm

New pull request New
442 Open 6,015 Closed
442 Open 6,015 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

[CI/Build] Remove limitation of NVCC_THREADS and MAX_JOBS > CPU count ci/build
#13606 opened Feb 20, 2025 by paul-grundmann Loading…
1
[Kernel][Minor] Refactor macro parameter naming for consistency
#13605 opened Feb 20, 2025 by haochengxia Loading…
1
[Misc] Upgrade transformers to 4.49 ci/build documentation Improvements or additions to documentation
#13602 opened Feb 20, 2025 by ywang96 Loading…
3
[Platform] Refactor memory manage function in memory_profiling to Platform
#13599 opened Feb 20, 2025 by ji-huazhong Loading…
1
[V1][Minor] Print KV cache size in token counts v1
#13596 opened Feb 20, 2025 by WoosukKwon Loading…
2
[MISC] optimizing _calc_mrope_positions needs-rebase v1
#13595 opened Feb 20, 2025 by kevin-can Loading…
2
[Bugfix] V1 Memory Profiling: V0 Sampler Integration without Rejection Sampler v1
#13594 opened Feb 20, 2025 by JenZhao Loading…
1
4
Bump up the transformers version to v4.49.0 ci/build documentation Improvements or additions to documentation ready ONLY add when PR is ready to merge/full CI is needed
#13592 opened Feb 20, 2025 by WoosukKwon Loading…
6
[core] set up data parallel communication ci/build v1
#13591 opened Feb 20, 2025 by youkaichao • Draft
2
fix neuron performance issue
#13589 opened Feb 20, 2025 by ajayvohra2005 Loading…
2
Integrating torchao quantization into vllm
#13588 opened Feb 20, 2025 by jerryzh168 Loading…
2
[V1][Sampler] Avoid an operation during temperature application v1
#13587 opened Feb 20, 2025 by njhill Loading…
4
[Bugfix][CPU] Fix cpu all-reduce using native pytorch implementation ready ONLY add when PR is ready to merge/full CI is needed
#13586 opened Feb 20, 2025 by Isotr0py Loading…
2
[Model] Merged multimodal processor for Paligemma needs-rebase
#13584 opened Feb 20, 2025 by kylehh Loading…
2
Switching test jobs into the amd_mi300 queue. // EXPERIMENTATION NO NEED TO MERGE ci/build
#13576 opened Feb 20, 2025 by Alexei-V-Ivanov-AMD Loading…
2
[Bugfix] Change disaggregated prefill example model name reflecting the change on HF
#13573 opened Feb 20, 2025 by TristonC Loading…
2
[NVIDIA] Support nvfp4 cutlass gemm ci/build
#13571 opened Feb 19, 2025 by kaixih Loading…
5
[WIP] Use uv python for docker ci/build
#13569 opened Feb 19, 2025 by mgoin Loading…
2
[HTTP Server] Make model param optional in request frontend
#13568 opened Feb 19, 2025 by youngkent Loading…
1
[Bugfix] Fix quantization skip modules logic
#13562 opened Feb 19, 2025 by jeejeelee • Draft
2 tasks
1
Remove unused kwargs from model definitions documentation Improvements or additions to documentation ready ONLY add when PR is ready to merge/full CI is needed speculative-decoding v1
#13555 opened Feb 19, 2025 by hmellor Loading…
3
[XPU]fix setuptools version for xpu ci/build
#13548 opened Feb 19, 2025 by yma11 Loading…
7
fix(chunked prefill): don't schedule prefill if freeing kv cache
#13539 opened Feb 19, 2025 by toslunar Loading…
1
4
[Frontend] Add backend-specific options for guided decoding documentation Improvements or additions to documentation ready ONLY add when PR is ready to merge/full CI is needed structured-output
#13505 opened Feb 19, 2025 by joerunde Loading…
@mgoin
9
[V1][Metrics] Implement vllm:lora_requests_info metric v1
#13504 opened Feb 18, 2025 by markmc Loading…
1
ProTip! Type g i on any issue or pull request to go back to the issue listing page.