Skip to content

Pull requests: vllm-project/vllm

New pull request New
687 Open 8,564 Closed
687 Open 8,564 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

[Misc] fix: add miss best_of param validation
#18555 opened May 22, 2025 by googs1025 Loading…
3
[Hardware][HPU] correct inference_mode method signature
#18551 opened May 22, 2025 by andyxning Loading…
2
[Feature] Support multiple api keys in server frontend
#18548 opened May 22, 2025 by Yanpas Loading…
1
[Bugfix] handle zero-token batches by creating empty attention metadata for KV cache load v1
#18545 opened May 22, 2025 by hammersam Loading…
1
1
[Hardware][CPU] Update intel_extension_for_pytorch 2.7.0 and move to requirements/cpu.txt ci/build
#18542 opened May 22, 2025 by yankay Loading…
1
3
[Model][Speculative Decoding] Integrate PARD into vLLM speculative-decoding
#18541 opened May 22, 2025 by zihaoanllm Loading…
1
Use prebuilt FlashInfer x86_64 PyTorch 2.7 CUDA 12.8 wheel for CI ci/build
#18537 opened May 22, 2025 by huydhn Loading…
2
optimize get_kv_cache_torch_dtype
#18531 opened May 22, 2025 by chunxiaozheng Loading…
1
[BUGFIX] fix layout shape of moe 2stage
#18523 opened May 22, 2025 by zhiding512 Loading…
1
Remove Vision FA warning
#18522 opened May 22, 2025 by vrdn-23 Loading…
1
4
Add reorder_batch to TPU V1 ready ONLY add when PR is ready to merge/full CI is needed tpu Related to Google TPUs v1
#18515 opened May 22, 2025 by mgoin Loading…
1
[Neuron] Remove bypass on EAGLEConfig and add a test
#18514 opened May 22, 2025 by elaineyz Loading…
3
[Misc][Benchmark] Add support for CustomDataset
#18511 opened May 21, 2025 by ekagra-ranjan Loading…
1
[Doc] fix typos in cutlass fp4 moe mm docstring
#18510 opened May 21, 2025 by ColinPeppler Loading…
1
[Misc][Benchmark] Fix save detailed
#18509 opened May 21, 2025 by ekagra-ranjan Loading…
1
Fix: Proper RGBA -> RGB conversion for PIL images. multi-modality Related to multi-modality (#4194)
#18508 opened May 21, 2025 by ChenheliHua Loading…
6
[Doc] Update quickstart and install for cu128 using --torch-backend=auto documentation Improvements or additions to documentation
#18505 opened May 21, 2025 by mgoin Loading…
1
[Bugfix] Fix spec decode on non-cuda platforms speculative-decoding
#18501 opened May 21, 2025 by rand-fly Loading…
1
[VLM] Initialize video input support for InternVL models documentation Improvements or additions to documentation frontend multi-modality Related to multi-modality (#4194)
#18499 opened May 21, 2025 by Isotr0py Loading…
1
10
Add Apple Silicon bf16 Support ci/build
#18497 opened May 21, 2025 by rahuja23 Loading…
3 tasks done
1
Draft: [P/D] Get P/D working w/ DP v1
#18495 opened May 21, 2025 by wseaton Loading…
2
Enable hybrid attention models for Transformers backend documentation Improvements or additions to documentation ready ONLY add when PR is ready to merge/full CI is needed
#18494 opened May 21, 2025 by hmellor Loading…
9
[Spec Decode] Make EAGLE3 draft token ID mapping optional v1
#18488 opened May 21, 2025 by benchislett Loading…
6
[P/D][Core] Fix abrupt request abort v1
#18485 opened May 21, 2025 by NickLucche Loading…
2
[Misc] refactor: simplify input validation and num_requests handling in _convert_v1_inputs frontend ready ONLY add when PR is ready to merge/full CI is needed
#18482 opened May 21, 2025 by googs1025 Loading…
9
ProTip! Add no:assignee to see everything that’s not assigned.