Skip to content

Pull requests: vllm-project/vllm

New pull request New
1,739 Open 19,048 Closed
1,739 Open 19,048 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
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

fix(models): apply embedding_multiplier to inputs_embeds in GraniteMoeHybrid
#35026 opened Feb 21, 2026 by nightcityblade Loading…
1
2
[Refactor] Simplify dummy data generation deepseek Related to DeepSeek models documentation Improvements or additions to documentation llama Related to Llama models multi-modality Related to multi-modality (#4194) qwen Related to Qwen models ready ONLY add when PR is ready to merge/full CI is needed speculative-decoding
#35025 opened Feb 21, 2026 by DarkLight1337 Loading…
5 tasks
9
[Deprecation] Remove old locations of get_tokenizer and resolve_hf_chat_template frontend ready ONLY add when PR is ready to merge/full CI is needed
#35024 opened Feb 21, 2026 by DarkLight1337 • Draft
5 tasks
3
[Core] Support structured outputs for beam search frontend
#35022 opened Feb 21, 2026 by guan404ming • Draft
3 of 5 tasks
6
[GGUF] Fix loading of fused/shard-less quantized weights
#35019 opened Feb 21, 2026 by laudney Loading…
2 of 3 tasks
1
perf(v1): optimize InputBatch.swap_states by swapping active token prefixes v1
#35018 opened Feb 21, 2026 by VedantMadane Loading…
5
Add support for DeepSeek Attention replay on CUDA deepseek Related to DeepSeek models fb-exported meta-exported nvidia
#35017 opened Feb 21, 2026 by maazmusameta Loading…
3
Add env variable VLLM_DISABLE_FLASHINFER_CONCAT_MLA_K to disable FlashInfer concat_mla_k fb-exported meta-exported
#35016 opened Feb 21, 2026 by maazmusameta Loading…
3
[Feature] Add per-request attention capture to the OpenAI-compatible API documentation Improvements or additions to documentation frontend v1
#35014 opened Feb 21, 2026 by Parkprogrammer Loading…
1
18
[CI/Build] Fix gRPC version mismatch ci/build ready ONLY add when PR is ready to merge/full CI is needed rocm Related to AMD ROCm
#35013 opened Feb 21, 2026 by DarkLight1337 Loading…
5 tasks
5
[XPU] Avoid use top_k_top_p_triton kernel for xpu ready ONLY add when PR is ready to merge/full CI is needed v1
#35011 opened Feb 21, 2026 by jikunshang Loading…
5 tasks
1
3
[XPU] allow TORCH_SDPA/TRITON_ATTN as XPU vit Backend
#35010 opened Feb 21, 2026 by yma11 Loading…
5
update-pillow-version to mitigate CVE-2026-25990 ci/build
#35009 opened Feb 21, 2026 by to-curiosity Loading…
11
[CI] Bumping grpcio version ci/build needs-rebase rocm Related to AMD ROCm
#35008 opened Feb 21, 2026 by AndreasKaratzas Loading…
5
[Bugfix] Register VLLM_BATCH_INVARIANT in envs.py to fix spurious unknown env var warning bug Something isn't working
#35007 opened Feb 21, 2026 by WindChimeRan Loading…
3 of 5 tasks
5
[Core]Optimize SlidingWindowManager.find_longest_cache_hit by skipping positions on cache miss v1
#35006 opened Feb 21, 2026 by lichuang Loading…
5 tasks
1
Fixing matcher to enable the 2-node-tests-4-gpus-in-total on MI355 ci/build
#35002 opened Feb 20, 2026 by Alexei-V-Ivanov-AMD Loading…
3
feat(model): add embed_sparse task for BGE-M3 server-side sparse aggr… frontend
#35001 opened Feb 20, 2026 by joeqzzuo Loading…
3 of 5 tasks
10
[CI] Fix tests/evals/gsm8k/test_gsm8k_correctness.py for Qwen3-Next-80B-A3B-NVFP4-EP2 qwen Related to Qwen models ready ONLY add when PR is ready to merge/full CI is needed v1
#34999 opened Feb 20, 2026 by LucasWilkinson Loading…
1
5
[ROCm] Check that AITER MHA is not selected with sinks rocm Related to AMD ROCm
#34998 opened Feb 20, 2026 by gshtras Loading…
1
[RL] Validation for pause_mode='keep' documentation Improvements or additions to documentation ready ONLY add when PR is ready to merge/full CI is needed
#34992 opened Feb 20, 2026 by hao-aaron Loading…
5 tasks
22
[Bugfix] ep_scatter kernel store-load race condition bug Something isn't working
#34991 opened Feb 20, 2026 by ivanium Loading…
5 tasks
7
[CI] Skip Responses API ci-failure Issue about an unexpected test failure in CI ready ONLY add when PR is ready to merge/full CI is needed
#34990 opened Feb 20, 2026 by robertgshaw2-redhat Loading…
5
[CI Bugfix] Add pytest.mark.flaky to tests/v1/e2e/test_spec_decode.py bug Something isn't working ci-failure Issue about an unexpected test failure in CI ready ONLY add when PR is ready to merge/full CI is needed v1
#34987 opened Feb 20, 2026 by mgoin Loading…
5 tasks
1
4
Trtllm gen full attn test coverage nvidia v1
#34986 opened Feb 20, 2026 by ojhaanshika • Draft
2
ProTip! Add no:assignee to see everything that’s not assigned.