Skip to content

Pull requests: vllm-project/vllm

New pull request New
780 Open 10,053 Closed
780 Open 10,053 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
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

Remove Qwen Omni workaround that's no longer necessary qwen Related to Qwen models ready ONLY add when PR is ready to merge/full CI is needed
#21057 opened Jul 16, 2025 by hmellor Loading…
2
[Feature][EPLB] Add EPLB support for MiniMax-01
#21056 opened Jul 16, 2025 by haveheartt Loading…
1 of 4 tasks
2
[Bugfix]: Fix final_res_batch list index out of range error frontend
#21055 opened Jul 16, 2025 by chaunceyjiang Loading…
8
[Frontend] Add explicit validation of tool length when tool_choice="required" in OpenAI server frontend
#21052 opened Jul 16, 2025 by n0gu-furiosa Loading…
3
[fix] fix qwen image_embeds input qwen Related to Qwen models ready ONLY add when PR is ready to merge/full CI is needed
#21049 opened Jul 16, 2025 by h-avsha Loading…
5
[V1] [KVConnector] Fix MultiprocExecutor worker output aggregation v1
#21048 opened Jul 16, 2025 by sdavidbd Loading…
2
Add test case for compiling multiple graphs
#21044 opened Jul 16, 2025 by sarckk Loading…
3 of 4 tasks
5
[Model] Reasoning Parser for Nemotron Models
#21041 opened Jul 16, 2025 by schoennenbeck Loading…
2
Fix minor docs issues and fix metric requests documentation Improvements or additions to documentation v1
#21040 opened Jul 16, 2025 by SriRangaTarun • Draft
3
[XPU] Add xpu support for fusion and collective fusion
#21036 opened Jul 16, 2025 by chaojun-zhang Loading…
4 tasks
6
[Feature][EPLB] Add eplb support for Qwen2 qwen Related to Qwen models
#21035 opened Jul 16, 2025 by lengrongfu • Draft
1 of 4 tasks
3
Add tokenization_kwargs to encode for embedding model truncation v1
#21033 opened Jul 16, 2025 by Receiling Loading…
3
[bugfix][WIP] Fix auto thread-binding when world_size > 1 in CPU backend and refactor code ci/build documentation Improvements or additions to documentation v1
#21032 opened Jul 16, 2025 by bigPYJ1151 Loading…
1 of 4 tasks
6
Enable sequence parallelism for full cuda graph without specifying compile sizes
#21031 opened Jul 16, 2025 by cascade812 Loading…
8
[Bugfix] weight loading use correct tp_group with patch_tensor_parallel_group
#21024 opened Jul 16, 2025 by Kevin-XiongC Loading…
4 tasks
2
Add the instruction to run e2e validation manually before release documentation Improvements or additions to documentation
#21023 opened Jul 16, 2025 by huydhn Loading…
4 tasks done
3
[XPU] Enable external_launcher to serve as an executor via torchrun v1
#21021 opened Jul 16, 2025 by chaojun-zhang Loading…
4 tasks
5
[Misc] Minor comment reorganization in capture_model() v1
#21015 opened Jul 15, 2025 by ruisearch42 Loading…
3 of 4 tasks
2
[Docker] Allow FlashInfer to be built in the ARM CUDA Dockerfile ci/build ready ONLY add when PR is ready to merge/full CI is needed
#21013 opened Jul 15, 2025 by mgoin Loading…
4 tasks
4
Update PyTorch to torch==2.7.1 for CUDA ci/build ready ONLY add when PR is ready to merge/full CI is needed
#21011 opened Jul 15, 2025 by mgoin Loading… v0.10.0
7
[protocol] Add request_id to the Request object so they can be controlled better via external load balancers frontend ready ONLY add when PR is ready to merge/full CI is needed
#21009 opened Jul 15, 2025 by kouroshHakha Loading…
4 tasks
5
[Not for merge] Unshift eagle prefill documentation Improvements or additions to documentation llama Related to Llama models needs-rebase new-model Requests to new models speculative-decoding v1
#21008 opened Jul 15, 2025 by morgendave • Draft
4 tasks
7
[Core] Avoid KVCacheBlock.__eq__ invocations in FreeKVCacheBlockQueue performance Performance-related issues v1
#21005 opened Jul 15, 2025 by JialinOuyang-Meta Loading…
7
Support mnnvl all2allv from Flashinfer needs-rebase
#21003 opened Jul 15, 2025 by wenscarl • Draft
4 tasks
9
Start using py3.12 for TPU. ci/build documentation Improvements or additions to documentation tpu Related to Google TPUs
#21000 opened Jul 15, 2025 by vanbasten23 Loading…
3 of 4 tasks
4
ProTip! Type g i on any issue or pull request to go back to the issue listing page.