Skip to content

Pull requests: vllm-project/vllm

New pull request New
479 Open 5,372 Closed
479 Open 5,372 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

[V1][Bugfix] Fix assertion when mm hashing is turned off ready ONLY add when PR is ready to merge/full CI is needed
#12439 opened Jan 26, 2025 by ywang96 Loading…
2
[Bugfix][Kernel] Fix perf regression caused by PR #12405 ci/build
#12434 opened Jan 26, 2025 by LucasWilkinson Loading…
4
Revert "[Misc] Add FA2 support to ViT MHA layer (#12355)" ready ONLY add when PR is ready to merge/full CI is needed
#12433 opened Jan 26, 2025 by WoosukKwon Loading…
2
[Platform] add pre_register_and_update function
#12432 opened Jan 26, 2025 by wangxiyuan Loading…
1
add support for AMD MI25/50/60
#12431 opened Jan 26, 2025 by Said-Akbar Loading…
1
[Frontend] Support scores endpoint in run_batch frontend
#12430 opened Jan 25, 2025 by pooyadavoodi Loading…
3
[Bugfix] Fix tqdm progress bar when SamplingParams.n > 1 frontend
#12428 opened Jan 25, 2025 by yanyc428 Loading…
1
1
[Build/CI] Fix libcuda.so linkage ci/build ready ONLY add when PR is ready to merge/full CI is needed
#12424 opened Jan 25, 2025 by tlrmchlsmth Loading…
4
[ROCm][AMD][Model] llama 3.2 support upstreaming
#12421 opened Jan 24, 2025 by maleksan85 Loading…
5
Fix the pydantic logging validator frontend
#12420 opened Jan 24, 2025 by maxdebayser Loading…
3
[Misc] Add offline test for disaggregated prefill
#12418 opened Jan 24, 2025 by Shaoting-Feng Loading…
8
[Bugfix] Disable w16a16 2of4 sparse CompressedTensors24 ready ONLY add when PR is ready to merge/full CI is needed
#12417 opened Jan 24, 2025 by tlrmchlsmth Loading…
6
[V1][Metrics] Add initial Prometheus logger ready ONLY add when PR is ready to merge/full CI is needed
#12416 opened Jan 24, 2025 by markmc • Draft
7
[V1] Revert uncache_blocks and support recaching full blocks ready ONLY add when PR is ready to merge/full CI is needed
#12415 opened Jan 24, 2025 by comaniac Loading…
1
[Usage] Add pipeline parallelism for usage stats
#12414 opened Jan 24, 2025 by simon-mo Loading…
3
[Frontend] Support override generation config in args ready ONLY add when PR is ready to merge/full CI is needed
#12409 opened Jan 24, 2025 by liuyanyi Loading…
5
[Bugfix] Fix benchmark script bug: inaccurate stats for vllm backend when max_model_len < input_len + output_len
#12407 opened Jan 24, 2025 by WangErXiao Loading…
1
[ci/build] detect and auto use cxx abi ci/build
#12403 opened Jan 24, 2025 by youkaichao Loading…
5
[MISC] add arg pad_for_invariant_seq_len
#12397 opened Jan 24, 2025 by MengqingCao Loading…
1
[Bugfix] Fix output_tokens is 0 if using tgi backend
#12394 opened Jan 24, 2025 by sywangyi Loading…
6
[torch.compile] PyTorch 2.6 and nightly compatibility
#12393 opened Jan 24, 2025 by youkaichao Loading…
3
[Hardware][Intel GPU] add XPU bf16 support documentation Improvements or additions to documentation ready ONLY add when PR is ready to merge/full CI is needed
#12392 opened Jan 24, 2025 by jikunshang Loading…
3
[V1][Core] Structured decoding on scheduler-level
#12388 opened Jan 24, 2025 by aarnphm • Draft
2
[Misc] Add BNB quantization for Whisper
#12381 opened Jan 24, 2025 by jeejeelee Loading…
2
[Frontend] Rerank API (Jina- and Cohere-compatible API) documentation Improvements or additions to documentation frontend
#12376 opened Jan 24, 2025 by K-Mistele Loading…
1
@DarkLight1337
32
ProTip! Find all pull requests that aren't related to any open issues with -linked:issue.