Skip to content

Pull requests: vllm-project/vllm

New pull request New
487 Open 5,444 Closed
487 Open 5,444 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] Gracefully handle huggingface hub http error
#12571 opened Jan 30, 2025 by ywang96 Loading…
3
Fix for attention layers to remain unquantized during moe_wn16 quant
#12570 opened Jan 30, 2025 by srikanthsrnvs Loading…
1
[V1][Log] Add max request concurrency log to V1 ready ONLY add when PR is ready to merge/full CI is needed
#12569 opened Jan 30, 2025 by mgoin Loading…
1
vllm-flash-attn build on AMD ci/build
#12566 opened Jan 29, 2025 by ProExpertProg • Draft
3
[Bugfix] Fix the device string for MoE models.
#12565 opened Jan 29, 2025 by elfiegg Loading…
2
[Misc] fix typo: add missing space in lora adapter error message frontend ready ONLY add when PR is ready to merge/full CI is needed
#12564 opened Jan 29, 2025 by Beim Loading…
2
[Feature] Fix guided decoding blocking bitmask memcpy performance Performance-related issues ready ONLY add when PR is ready to merge/full CI is needed structured-output
#12563 opened Jan 29, 2025 by xpbowler Loading…
3
[Bugfix/CI] Fixup benchmark_moe.py
#12562 opened Jan 29, 2025 by tlrmchlsmth Loading…
1
[CPU][PPC] Updated torch, torchvision, torchaudio dependencies ci/build ready ONLY add when PR is ready to merge/full CI is needed
#12555 opened Jan 29, 2025 by npanpaliya Loading…
3
[VLM] Merged multi-modal processor for InternVL-based models documentation Improvements or additions to documentation
#12553 opened Jan 29, 2025 by DarkLight1337 Loading…
9
[Misc] O3 compilation and Spec Decoding are not compatible
#12551 opened Jan 29, 2025 by NickLucche Loading…
8
[Bugfix] fix vocab size assertion frontend
#12550 opened Jan 29, 2025 by schlaepf Loading…
1
Move requirements into their own directory ci/build documentation Improvements or additions to documentation
#12547 opened Jan 29, 2025 by hmellor Loading…
2
[Bugfix] Fix 'ModuleNotFoundError: No module named 'intel_extension_for_pytorch'' for --tensor-parallel-size more than 1
#12546 opened Jan 29, 2025 by Akashcodes732 Loading…
1
2
[do not merge] V1 scheduler interface
#12544 opened Jan 29, 2025 by WoosukKwon • Draft
1
[do not merge]
#12540 opened Jan 29, 2025 by WoosukKwon • Draft
1
[Bugfix][Spec Decode] fix: update logits processor for MQA scoring
#12537 opened Jan 29, 2025 by llsj14 Loading…
1
5
[Kernel] Use self.kv_cache and forward_context.attn_metadata in Attention.forward
#12536 opened Jan 29, 2025 by heheda12345 Loading…
1
4
[WIP][AMD][Kernel][Quantization] Add fp8 and int8 support for Triton FAv2 kernel documentation Improvements or additions to documentation
#12534 opened Jan 29, 2025 by rasmith • Draft
3
[Attention] MLA decode optimizations ci/build
#12528 opened Jan 28, 2025 by LucasWilkinson Loading…
25
Add label if pre-commit passes ci/build
#12527 opened Jan 28, 2025 by hmellor • Draft
10
layerwise KV transfer in PD Disaggregation
#12523 opened Jan 28, 2025 by chenqianfzh Loading…
6
[Kernel] Add ModelOpt NVFP4 Checkpoint Support
#12520 opened Jan 28, 2025 by pavanimajety • Draft
1
[Kernel] Add Kernel Support for NVFP4 ci/build
#12519 opened Jan 28, 2025 by pavanimajety • Draft
12
[RFC][vllm-API] Support tokenizer registry for customized tokenizer in vLLM frontend
#12518 opened Jan 28, 2025 by youngkent Loading…
@DarkLight1337
5
ProTip! Mix and match filters to narrow down what you’re looking for.