Skip to content

Pull requests: vllm-project/vllm

New pull request New
482 Open 6,381 Closed
482 Open 6,381 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

[Bugfix] Fix validation of logprobs in ChatCompletionRequest frontend
#14352 opened Mar 6, 2025 by schoennenbeck Loading…
1
1
[Misc][Docs] fix the comments of KV_T and CACHE_T in CALL_RESHAPE_AND_CACHE_XX macros
#14347 opened Mar 6, 2025 by yangsijia-serena Loading…
1
[CI] Disable spawn when running V1 Test ci/build
#14345 opened Mar 6, 2025 by tdoublep Loading…
1
[Misc] Add Phi4-MM example documentation Improvements or additions to documentation
#14343 opened Mar 6, 2025 by jeejeelee Loading…
4
OpenVINO: added CPU-like conditions
#14338 opened Mar 6, 2025 by ilya-lavrenov Loading…
1
[Core] Optimize multi-modal profiling
#14336 opened Mar 6, 2025 by DarkLight1337 • Draft
1
Use the optimized block sizes after tuning the kernel. v1
#14329 opened Mar 6, 2025 by vanbasten23 • Draft
1
[Misc] Ensure out-of-tree quantization method recognize by cli args
#14328 opened Mar 6, 2025 by liuyanyi Loading…
1
fix minor miscalled method
#14327 opened Mar 6, 2025 by kushanam Loading…
1
[Bugfix][Core] fix abort_seq_group and memory leak when n>1
#14326 opened Mar 6, 2025 by courage17340 Loading…
2
[Model] Add PLaMo2 ci/build
#14323 opened Mar 6, 2025 by Alnusjaponica Loading…
2
Revert "[torch.compile] Fix RMSNorm + quant fusion in the non-cutlass…
#14317 opened Mar 5, 2025 by tlrmchlsmth Loading…
1
[ROCm] Enable chunked prefill/paged attention in MLA on ROCm
#14316 opened Mar 5, 2025 by SageMoore Loading…
4
[Bug] Fix Attention when ignored in by quant_method
#14313 opened Mar 5, 2025 by mgoin Loading…
1
[Core] Expose API endpoint /is_sleeping frontend v1
#14312 opened Mar 5, 2025 by waltforme • Draft
1
1
[Hardware][TPU]Enable ragged paged attention kernel and resolve recompilation issue v1
#14310 opened Mar 5, 2025 by yaochengji • Draft
5
[V1] TPU - Remove self.kv_caches documentation Improvements or additions to documentation v1
#14309 opened Mar 5, 2025 by alexm-redhat Loading…
4
[Kernel] Add needs_fixed_stride_order tag to most GEMMs
#14306 opened Mar 5, 2025 by tlrmchlsmth Loading…
4
[Distributed] Add enable_expert_parallel arg documentation Improvements or additions to documentation
#14305 opened Mar 5, 2025 by tlrmchlsmth Loading…
1
[Docs] Add nsight guide to profiling docs documentation Improvements or additions to documentation
#14298 opened Mar 5, 2025 by mgoin Loading…
1
[Build] Cython compilation support fix ci/build
#14296 opened Mar 5, 2025 by gshtras Loading…
4
[Model] add colqwen2_vl code & inference documentation Improvements or additions to documentation
#14291 opened Mar 5, 2025 by BloomBerry Loading…
2
[MISC] Refine no available block debug msg
#14287 opened Mar 5, 2025 by yiliu30 Loading…
1
[MISC] rename interval to max_recent_requests ready ONLY add when PR is ready to merge/full CI is needed v1
#14285 opened Mar 5, 2025 by andyxning Loading…
3
[Misc] Set default value of seed to None frontend ready ONLY add when PR is ready to merge/full CI is needed
#14274 opened Mar 5, 2025 by SmartManoj Loading…
2
ProTip! Updated in the last three days: updated:>2025-03-03.