Skip to content

Pull requests: vllm-project/vllm

New pull request New
538 Open 7,223 Closed
538 Open 7,223 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

[Benchmark][Doc] Update throughput benchmark and README
#15998 opened Apr 3, 2025 by StevenShi-23 Loading…
1
[Bugfix][kernels] Fix half2float conversion in gguf kernels ready ONLY add when PR is ready to merge/full CI is needed
#15995 opened Apr 3, 2025 by Isotr0py Loading…
1
[Core][LoRA] Add LoRA for EncoderDecoderModelRunner
#15990 opened Apr 3, 2025 by jeejeelee • Draft
1
Use custom address for listening socket
#15988 opened Apr 3, 2025 by jglaser Loading…
1
1
fix: close issue #15985 for tricky import ci/build
#15986 opened Apr 3, 2025 by yihong0618 Loading…
1
1
[TPU] Switch Test to Non-Sliding Window ready ONLY add when PR is ready to merge/full CI is needed tpu Related to Google TPUs
#15981 opened Apr 3, 2025 by robertgshaw2-redhat Loading…
2
[V1] DP scale-out (2/N): Decouple engine process management and comms v1
#15977 opened Apr 3, 2025 by njhill • Draft
2
[V0][V1][Core] Add outlines integration for V1, and update V0 integration. v1
#15975 opened Apr 3, 2025 by unaidedelf8777 • Draft
2
[Misc] improve gguf check
#15974 opened Apr 3, 2025 by reidliu41 Loading…
4
[BUGFIX] resolve bug preventing lm_eval working with vllm v1 engine v1
#15971 opened Apr 2, 2025 by brian-dellabetta Loading…
2
Revert "Add minimum version for huggingface_hub to enable Xet downloads" ci/build needs-rebase ready ONLY add when PR is ready to merge/full CI is needed
#15963 opened Apr 2, 2025 by robertgshaw2-redhat Loading…
8
[Model] Allow more customization in LlamaForCausalLM
#15962 opened Apr 2, 2025 by luccafong • Draft
2
Add support to modelopt quantization of Mixtral model
#15961 opened Apr 2, 2025 by yueshen2016 Loading…
1
[Core][P/D Disagg] KV Connector API for v1 disaggregated prefill support ci/build documentation Improvements or additions to documentation v1
#15960 opened Apr 2, 2025 by ApostaC Loading…
5
DeepGemm MoE expert map support
#15957 opened Apr 2, 2025 by bnellnm • Draft
1
Modular fused experts
#15956 opened Apr 2, 2025 by bnellnm • Draft
1
[SupportsQuant] Chameleon, Chatglm, Commandr ci/build documentation Improvements or additions to documentation frontend structured-output v1
#15952 opened Apr 2, 2025 by kylesayrs Loading…
2
[Frontend] Support guidance:no-additional-properties for compatibility with xgrammar structured-output
#15949 opened Apr 2, 2025 by tjohnson31415 Loading…
2
[Bugfix] fix use_atomic_add support of marlin kernel when using v1 engine
#15946 opened Apr 2, 2025 by jinzhen-lin Loading…
1
[Hardware][Gaudi][BugFix] fix arguments of hpu fused moe
#15945 opened Apr 2, 2025 by zhenwei-intel Loading…
1
[Model] use AutoWeightsLoader for baichuan, gpt-neox, mpt
#15939 opened Apr 2, 2025 by jonghyunchoe Loading…
1
3
[Bugfix] Enforce Ray backend for TPU/HPU as documented.
#15937 opened Apr 2, 2025 by gitover22 Loading…
1
[WIP][Kernel] Enable FP16 and BF16 CUTLASS MoE kernels
#15932 opened Apr 2, 2025 by ElizaWszola • Draft
9
Fixed Stream set to True, client stream receiving arguments, concatenated json string, missing curly braces end frontend
#15930 opened Apr 2, 2025 by xiaodizi Loading…
2
[doc] update contribution link documentation Improvements or additions to documentation
#15922 opened Apr 2, 2025 by reidliu41 Loading…
3
ProTip! What’s not been updated in a month: updated:<2025-03-03.