Skip to content

Pull requests: vllm-project/vllm

New pull request New
438 Open 4,918 Closed
438 Open 4,918 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

[Misc] Minimum requirements for SageMaker compatibility ci/build frontend
#11576 opened Dec 28, 2024 by nathan-az Loading…
1
1
[Draft] Update benchmark_moe.py to use block wise quant for Deepseek V3
#11574 opened Dec 28, 2024 by simon-mo • Draft
2
[benchmark] Remove dependency for H100 benchmark step ci/build
#11572 opened Dec 27, 2024 by khluu Loading…
1
[Model] Support InternLM2 Reward models documentation Improvements or additions to documentation
#11571 opened Dec 27, 2024 by Isotr0py Loading…
1
[Frontend] Improve Error Handling documentation Improvements or additions to documentation frontend needs-rebase
#11570 opened Dec 27, 2024 by robertgshaw2-neuralmagic Loading…
2
[Bugfix] Move the _touch(computed_blocks) call in the allocate_slots method to after the check for allocating new blocks.
#11565 opened Dec 27, 2024 by sakunkun Loading…
1
5
[Model] LoRA with lm_head and embed_tokens fully trained - 3
#11558 opened Dec 27, 2024 by sergeykochetkov Loading…
1
[Misc]Minor Changes about Worker
#11555 opened Dec 27, 2024 by noemotiovon Loading…
1
[Frontend] [Bugfix] Refactor tool parsers and simplify the tool parsing interface. ci/build frontend
#11554 opened Dec 27, 2024 by elementary-particle • Draft
1
1
[Misc] Speculative Decoding: Adding Mean Accept Length Metric
#11552 opened Dec 27, 2024 by MMuzzammil1 Loading…
6
[V1] [5/N] API Server: unify Detokenizer and EngineCore input ready ONLY add when PR is ready to merge/full CI is needed
#11545 opened Dec 27, 2024 by robertgshaw2-neuralmagic Loading…
3
Bounded peak memory in Top-P-Top-K with chunked sorting ci/build
#11544 opened Dec 27, 2024 by yangalan123 Loading…
1
3
[Benchmark] Add benchmark script for CPU offloading ready ONLY add when PR is ready to merge/full CI is needed
#11533 opened Dec 26, 2024 by ApostaC Loading…
1
[Core] Block Allocator to support KV cache CPU offloading frontend ready ONLY add when PR is ready to merge/full CI is needed
#11532 opened Dec 26, 2024 by ApostaC Loading…
1
[Core] Performance optimization for swap_blocks by cuda kernels ready ONLY add when PR is ready to merge/full CI is needed
#11531 opened Dec 26, 2024 by ApostaC Loading…
1
[BugFix] Fix parameter names and process_after_weight_loading for W4A16 MoE Group Act Order
#11528 opened Dec 26, 2024 by dsikka Loading…
4
Fixed docker build for ppc64le ci/build
#11518 opened Dec 26, 2024 by npanpaliya Loading…
1
[Platform] Move get_punica_wrapper() function to Platform
#11516 opened Dec 26, 2024 by shen-shanshan • Draft
2
[Hardware][AMD]: Replace HIPCC version with more precise ROCm version ci/build rocm
#11515 opened Dec 26, 2024 by hj-wei Loading…
4
[V1] Add kv cache utils tests.
#11513 opened Dec 26, 2024 by xcnick Loading…
1
Add a helpful message when execution fails
#11504 opened Dec 26, 2024 by eldarkurtic Loading…
1
[prototype] V1 pp raycg proto needs-rebase
#11497 opened Dec 26, 2024 by ruisearch42 • Draft
2
Resolve race conditions in Marlin kernel
#11493 opened Dec 25, 2024 by wchen61 Loading…
2
2
[Misc] Use registry-based initialization for KV cache transfer connector.
#11481 opened Dec 25, 2024 by KuntaiDu Loading…
2
[Misc] Allow initializing KV cache transfer agent when using third-party library for disaggregated prefill
#11480 opened Dec 25, 2024 by KuntaiDu Loading…
1
ProTip! Adding no:label will show everything without a label.