Skip to content

Pull requests: vllm-project/vllm

New pull request New
456 Open 5,128 Closed
456 Open 5,128 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] [2/n] Logging and Metrics - OutputProcessor Abstraction
#11973 opened Jan 12, 2025 by robertgshaw2-neuralmagic Loading…
1
[CI][Spec Decode] fix: broken test for EAGLE model ci/build ready ONLY add when PR is ready to merge/full CI is needed
#11972 opened Jan 12, 2025 by llsj14 Loading…
7
[Misc] Support register quantization method out-of-tree
#11969 opened Jan 12, 2025 by ice-tong Loading…
1
1
[Kernel] Attention.forward with unified_attention when use_direct_call=True
#11967 opened Jan 12, 2025 by heheda12345 Loading…
1
[Spec Decode] feat: support LoRA with speculative decoding
#11966 opened Jan 12, 2025 by llsj14 Loading…
1
[V1][Core][1/n] Logging and Metrics ready ONLY add when PR is ready to merge/full CI is needed
#11962 opened Jan 11, 2025 by robertgshaw2-neuralmagic Loading…
7
[V1] Move more control of kv cache initialization from model_executor to EngineCore
#11960 opened Jan 11, 2025 by heheda12345 Loading…
@comaniac
1
[V1][Core] Add guided decoding in v1
#11955 opened Jan 11, 2025 by WangErXiao • Draft
1
[platform] add ray_device_key
#11948 opened Jan 11, 2025 by youkaichao Loading…
6
[Misc] Fix Deepseek V2 fp8 kv-scale remapping ready ONLY add when PR is ready to merge/full CI is needed
#11947 opened Jan 11, 2025 by Concurrensee Loading…
2
[Misc] Add helpers to get pipeline rank & world size
#11946 opened Jan 10, 2025 by ethnzhng Loading…
1
[Ignore] Test documentation Improvements or additions to documentation
#11944 opened Jan 10, 2025 by mgoin Loading…
1
[V1] Add prefix caching hit rate
#11942 opened Jan 10, 2025 by comaniac Loading…
1
[V1][WIP] Hybrid allocator for full attention & sliding window attention interleaved models (Reference PR, do not merge) needs-rebase
#11938 opened Jan 10, 2025 by heheda12345 • Draft
2
[WIP] [V1] TPU support needs-rebase
#11936 opened Jan 10, 2025 by alexm-neuralmagic Loading…
@alexm-neuralmagic
8
Organise installation documentation into categories and tabs documentation Improvements or additions to documentation
#11935 opened Jan 10, 2025 by hmellor Loading…
11
[RFC][Core] Cache policy framework
#11928 opened Jan 10, 2025 by ShawnD200 • Draft
3
[Misc] Merge bitsandbytes_stacked_params_mapping and packed_modules_mapping
#11924 opened Jan 10, 2025 by jeejeelee • Draft
1 task
1
[Doc] links Tensorizer example documentation Improvements or additions to documentation
#11918 opened Jan 10, 2025 by guspan-tanadi Loading…
8
[Doc] Correct the spelling of GitHub documentation Improvements or additions to documentation
#11915 opened Jan 10, 2025 by Yaminyam Loading…
3
[V1] APC + prompt logprobs unsupported (PR 2/N for v1 sample and prompt logprobs support)
#11910 opened Jan 10, 2025 by afeldman-nm Loading…
1
[FP8][Kernel] Dynamic kv cache scaling factors computation documentation Improvements or additions to documentation
#11906 opened Jan 9, 2025 by gshtras Loading…
1
[Model] Add T5 model (2/2)
#11901 opened Jan 9, 2025 by NickLucche Loading…
2
[Bugfix] Multi-sequence broken
#11898 opened Jan 9, 2025 by andylolu2 Loading…
7
[V1][Core] Autotune encoder cache budget
#11895 opened Jan 9, 2025 by ywang96 Loading…
28
ProTip! Filter pull requests by the default branch with base:main.