-
-
Notifications
You must be signed in to change notification settings - Fork 11.6k
Pull requests: vllm-project/vllm
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
[Model Runner V2] Refactor prefill token preparation
nvidia
v1
#29712
opened Nov 29, 2025 by
WoosukKwon
Loading…
SM120 / NVFP4: add device guard and runtime SM dispatch to cutlass_scaled_fp4_mm
nvidia
#29711
opened Nov 29, 2025 by
hholtmann
Loading…
[perf] Use direct copy (broadcast) instead of cat for k_nope/k_pe in MLA prefill
v1
#29710
opened Nov 29, 2025 by
minosfuture
Loading…
5 tasks
[KVConnector] remove unused code (the model aware kv ops class)
kv-connector
#29709
opened Nov 29, 2025 by
KuntaiDu
Loading…
5 tasks
[LoRA] Support FusedMoE LoRA Triton kernel for mxfp4
gpt-oss
Related to GPT-OSS models
ready
ONLY add when PR is ready to merge/full CI is needed
#29708
opened Nov 29, 2025 by
xyang16
Loading…
5 tasks
[KVConnector] Remove v0-related kv connector components such as kv pipe and kv lookup buffer
kv-connector
#29705
opened Nov 28, 2025 by
KuntaiDu
Loading…
5 tasks
[BugFix] Fix DBO failing with TypeError: 'NoneType' object is not iterable
ready
ONLY add when PR is ready to merge/full CI is needed
v1
#29698
opened Nov 28, 2025 by
LucasWilkinson
Loading…
FlashInfer-Bench Integration for vLLM
documentation
Improvements or additions to documentation
nvidia
#29695
opened Nov 28, 2025 by
sfc-gh-goliaro
•
Draft
4 of 11 tasks
[Misc] Convert Related to DeepSeek models
documentation
Improvements or additions to documentation
frontend
llama
Related to Llama models
multi-modality
Related to multi-modality (#4194)
performance
Performance-related issues
qwen
Related to Qwen models
ready
ONLY add when PR is ready to merge/full CI is needed
ready-run-all-tests
Trigger CI with all tests for wide-ranging PRs
structured-output
tool-calling
v1
TokenizerBase to protocol, consolidate tokenizer tests
ci/build
deepseek
#29693
opened Nov 28, 2025 by
DarkLight1337
Loading…
5 tasks
[Bugfix] Schedule failure due to wrong get_image_size_with_most_features
qwen
Related to Qwen models
#29692
opened Nov 28, 2025 by
tomtomjhj
Loading…
3 of 5 tasks
[WIP][Kernel]Support W4A8 Grouped GEMM on Hopper
ci/build
new-model
Requests to new models
nvidia
#29691
opened Nov 28, 2025 by
czhu-cohere
Loading…
5 tasks
[CI] Renovation of nightly wheel build & generation
ci/build
#29690
opened Nov 28, 2025 by
Harry-Chen
•
Draft
3 of 5 tasks
[Chore]: Remove Olmo3 and FlexOlmo config copy
ready
ONLY add when PR is ready to merge/full CI is needed
#29677
opened Nov 28, 2025 by
Isotr0py
Loading…
1 of 5 tasks
[CI/build] Add libraries needed for building VLLM wheel to the test docker image.
ci/build
#29672
opened Nov 28, 2025 by
halyavin
Loading…
5 tasks
hfrunner.classify should return list[list[float]] not list[str]
#29671
opened Nov 28, 2025 by
nwaughachukwuma
Loading…
[NIXL] Add remote_request_id to kv_transfer_params
kv-connector
ready
ONLY add when PR is ready to merge/full CI is needed
v1
#29665
opened Nov 28, 2025 by
markmc
Loading…
[Bugfix] Fix prefix_repetition routing in bench throughput
performance
Performance-related issues
#29663
opened Nov 28, 2025 by
jr-shen
Loading…
3 of 5 tasks
[CI] Prevents triggering of an inactive issue/PR check for forked repository.
ci/build
#29654
opened Nov 28, 2025 by
wzshiming
Loading…
5 tasks
fix potential object has no attribute 'bias' error
#29653
opened Nov 28, 2025 by
allerou4
Loading…
5 tasks
[Model] Add step-deepresearch tool parser
frontend
tool-calling
#29652
opened Nov 28, 2025 by
randzero
Loading…
3 of 5 tasks
[P/D] Add P/D disaggregation deployment on Ray
documentation
Improvements or additions to documentation
frontend
kv-connector
#29649
opened Nov 28, 2025 by
JackyMa1997
Loading…
5 tasks
[Core] Rename PassConfig flags as per RFC #27995
needs-rebase
v1
#29646
opened Nov 28, 2025 by
arpitkh101
Loading…
Previous Next
ProTip!
Follow long discussions with comments:>50.