Skip to content

Pull requests: vllm-project/vllm

New pull request New
412 Open 4,845 Closed
412 Open 4,845 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 issues for Pixtral-Large-Instruct-2411 ready ONLY add when PR is ready to merge/full CI is needed
#11393 opened Dec 21, 2024 by ywang96 Loading…
1
[Bugfix] Fix fully sharded LoRAs with Mixtral
#11390 opened Dec 21, 2024 by n1hility Loading…
1
[Bugfix] Use outlines for grammars that can't convert to GBNF
#11389 opened Dec 21, 2024 by mgoin Loading…
1
[Misc] Add assertion and helpful message for marlin24 compressed models
#11388 opened Dec 21, 2024 by dsikka Loading…
1
Update Dockerfile.rocm ci/build
#11387 opened Dec 20, 2024 by yx-lamini Loading…
1
[Core] Support global prefix caching
#11385 opened Dec 20, 2024 by lyppg Loading…
1
[Misc] Adding API Key to the benchmark
#11384 opened Dec 20, 2024 by bjb19 Loading…
3
[V1] Make AsyncLLMEngine v1-v0 opaque frontend ready ONLY add when PR is ready to merge/full CI is needed
#11383 opened Dec 20, 2024 by rickyyx Loading…
3
[Bugfix] Use .clone() for sampling params and deepcopy XGrammarLogitsProcessor
#11380 opened Dec 20, 2024 by tjohnson31415 • Draft
1
1
[Bugfix] Last token measurement fix
#11376 opened Dec 20, 2024 by rajveerb Loading…
1
4
[platform] Refactor current_memory_usage() function in DeviceMemoryProfiler into Platform
#11369 opened Dec 20, 2024 by shen-shanshan • Draft
1
[Frontend][Misc] Don't Repeat Yourself (DRY) Sampling frontend
#11368 opened Dec 20, 2024 by AlpinDale Loading…
1
1
[Bugfix]: only log extra fields for successfully deserialized objects frontend
#11367 opened Dec 20, 2024 by gcalmettes Loading…
3
[platform] Do not use current_platform in global namespace
#11362 opened Dec 20, 2024 by wangxiyuan Loading…
1
[Bugfix] Fix sliding window in cohere2 model
#11358 opened Dec 20, 2024 by CXIAAAAA Loading…
1
[Kernel] Add ExLlamaV2 Weight Quantization Support ci/build kernel quantization
#11348 opened Dec 19, 2024 by AlpinDale • Draft
1
4
[VLM] Support caching in merged multi-modal processor documentation Improvements or additions to documentation
#11341 opened Dec 19, 2024 by DarkLight1337 Loading…
@ywang96
2
[Kernel][Model] PagedAttention: Support custom attention bias for T5 model (1/2)
#11334 opened Dec 19, 2024 by NickLucche Loading…
4
DRAFT: Add transformers backend support ci/build
#11330 opened Dec 19, 2024 by ArthurZucker • Draft
4
[platform] support pytorch custom op pluggable
#11328 opened Dec 19, 2024 by wangxiyuan Loading…
1
[Distributed][refactor] Add base class for device-specific communicator
#11324 opened Dec 19, 2024 by MengqingCao Loading…
1
[platform] support custom torch.compile backend key
#11318 opened Dec 19, 2024 by wangxiyuan Loading…
1
[Core] Changes to support 0.2.0 flashinfer
#11314 opened Dec 19, 2024 by pavanimajety Loading…
2
Update Dockerfile.tpu pin to nightly torch_xla ci/build
#11309 opened Dec 18, 2024 by ManfeiBai Loading…
5
[Bugfix][CI] ALiBi test case in xformers multi_query_kv_attention
#11301 opened Dec 18, 2024 by NickLucche Loading…
1
ProTip! Mix and match filters to narrow down what you’re looking for.