Skip to content

Pull requests: vllm-project/vllm

New pull request New
1,260 Open 14,623 Closed
1,260 Open 14,623 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

fix cross attention v1
#28346 opened Nov 8, 2025 by fsx950223 Loading…
5 tasks
1
6
[Performance][gpt-oss] Revert gpt-oss max cudagraph size to 1024 gpt-oss Related to GPT-OSS models performance Performance-related issues ready ONLY add when PR is ready to merge/full CI is needed
#28345 opened Nov 8, 2025 by mmangkad Loading…
5 tasks
3
[Kernel] Fix fused_gdn_gating qwen Related to Qwen models
#28343 opened Nov 8, 2025 by ZJY0516 Loading…
5 tasks
11
fix: close issue 28338 by fixed python version ci/build
#28339 opened Nov 8, 2025 by yihong0618 Loading…
5 tasks
1
7
Remove setuptools upper bound constraint (<80) ci/build ready ONLY add when PR is ready to merge/full CI is needed rocm Related to AMD ROCm
#28337 opened Nov 8, 2025 by ColeMurray Loading…
1
6
[Misc] FlattenLogprobs -> FlatLogprobs ready ONLY add when PR is ready to merge/full CI is needed
#28335 opened Nov 8, 2025 by zhuohan123 Loading…
5 tasks
7
[Frontend] split append tool output frontend gpt-oss Related to GPT-OSS models
#28333 opened Nov 8, 2025 by qandrew Loading…
2
[Model] Add Afmoe architecture implementation documentation Improvements or additions to documentation new-model Requests to new models
#28332 opened Nov 8, 2025 by pranav4501 Loading…
5 tasks done
4
[Frontend][2/n] remove empty content from _parse_tool_calls_from_content frontend ready ONLY add when PR is ready to merge/full CI is needed
#28331 opened Nov 7, 2025 by qandrew Loading…
4
Fix: tool call streaming when both reasoning and tool parsers are enabled #28297 frontend
#28330 opened Nov 7, 2025 by baonudesifeizhai Loading…
5 tasks
5
[Misc] Add more scoping for improved trace v1
#28329 opened Nov 7, 2025 by frank-wei Loading…
4
Enhance run_cluster.sh for multi-NIC support documentation Improvements or additions to documentation
#28328 opened Nov 7, 2025 by evberrypi Loading…
2 of 4 tasks
4
[Core] Simplify async KV output aggregation kv-connector ready ONLY add when PR is ready to merge/full CI is needed v1
#28327 opened Nov 7, 2025 by njhill Loading…
4
[CI/Build] Temporary fix to LM Eval Small Models ci/build
#28324 opened Nov 7, 2025 by zhewenl Loading…
7
Fix rotary embedding benchmark script performance Performance-related issues
#28323 opened Nov 7, 2025 by xyang16 Loading…
5 tasks
4
[CI] lora/test_mixtral.py : Add additional expected outputs due to flakiness
#28322 opened Nov 7, 2025 by varun-sundar-rabindranath Loading…
4
[ROCm] Add env to enable/disable aiter triton gemm rocm Related to AMD ROCm
#28321 opened Nov 7, 2025 by sarckk Loading…
3 of 5 tasks
4
[WIP] Tmp fix for IMA with MTP = 2 and full-cg v1
#28315 opened Nov 7, 2025 by LucasWilkinson • Draft
6
Make tests/lora/utils usable by plugins
#28313 opened Nov 7, 2025 by vanbasten23 Loading…
5 tasks
2
[BugFix][CI/Build] Fix import error and apply assert in appropriate case in test_struct_output_generate structured-output v1
#28311 opened Nov 7, 2025 by rasmith Loading…
1
2
[Core] Send kv events from worker side to scheduler side kv-connector v1
#28309 opened Nov 7, 2025 by hickeyma Loading…
5 tasks
6
[Kernel] Support CUDA Graphs in 3D Triton Attention Kernel v1
#28306 opened Nov 7, 2025 by jvlunteren Loading…
4
[Core] Cache vllm_is_batch_invariant
#28304 opened Nov 7, 2025 by lgeiger Loading…
6
[Bugfix] Parse gpt-oss refusals w/ newer openai-harmony ci/build frontend gpt-oss Related to GPT-OSS models
#28303 opened Nov 7, 2025 by bbrowning Loading…
2
[Model][Qwen3VL] Simplify get_mrope_input_positions using numpy qwen Related to Qwen models
#28302 opened Nov 7, 2025 by lgeiger Loading…
3
ProTip! Mix and match filters to narrow down what you’re looking for.