Skip to content

Pull requests: vllm-project/vllm

New pull request New
3,432 Open 25,846 Closed
3,432 Open 25,846 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

[Bugfix] Fix Humming kernel weight conversion for unpacked CompressedTensors W4A8 INT checkpoints bug Something isn't working
#46136 opened Jun 19, 2026 by JOSH1024 Contributor Loading…
1
[HARDWARE][POWER] Enable fp16 support for PowerPC cpu Related to CPU backends
#46135 opened Jun 19, 2026 by Rukhaiya2004 Contributor Loading…
1
[Misc] Add unit test for merge_attn_states kernel
#46134 opened Jun 19, 2026 by pmanczak Loading…
1
[Bugfix] Handle GPU/MIG UUIDs in CUDA_VISIBLE_DEVICES bug Something isn't working nvidia
#46132 opened Jun 19, 2026 by fede-kamel Loading…
1
1
[Misc] Enable test_triton_scaled_mm on XPU intel-gpu Related to Intel GPU
#46130 opened Jun 19, 2026 by pmanczak Loading…
1
[Rust Frontend] Support truncate_prompt_tokens and truncation_side rust
#46129 opened Jun 19, 2026 by willamhou Contributor Loading…
3
[Misc] Add unit test for ep_gather kernel
#46128 opened Jun 19, 2026 by pmanczak Loading…
1
[Bugfix] Make Kimi's tool parser accept numeric only tool call IDs bug Something isn't working tool-calling
#46127 opened Jun 19, 2026 by rishaps Contributor Loading…
[ASR] Add Voice Activity Detection (VAD) ci/build frontend multi-modality Related to multi-modality (#4194) nvidia performance Performance-related issues
#46126 opened Jun 19, 2026 by ekagra-ranjan Contributor Loading…
Revert "Fix Stale Encoder Cache After Weight Update" frontend v1
#46125 opened Jun 19, 2026 by SumanthRH Contributor • Draft
[Bugfix] Parse MiniMax M3 visible reasoning markers bug Something isn't working tool-calling
#46124 opened Jun 19, 2026 by nightcityblade Contributor Loading…
4 tasks done
1
[ROCm][Perf] Optional FlyDSL BF16 MoE for the MXFP8-emulation path on MiniMax-M3 rocm Related to AMD ROCm
#46123 opened Jun 19, 2026 by yueliu14 • Draft
1
[ROCm] [Performance] Optimize aiter moe for DeepSeekV4 deepseek Related to DeepSeek models rocm Related to AMD ROCm
#46122 opened Jun 19, 2026 by tjtanaa Member Loading…
4 tasks
fix: resolve vLLM performance and API issues ci/build cpu Related to CPU backends deepseek Related to DeepSeek models documentation Improvements or additions to documentation frontend gpt-oss Related to GPT-OSS models kv-connector mistral Related to Mistral models multi-modality Related to multi-modality (#4194) new-model Requests to new models nvidia qwen Related to Qwen models rocm Related to AMD ROCm rust speculative-decoding tool-calling v1
#46120 opened Jun 19, 2026 by gmrnlg1971 Loading…
4 tasks
2
[Pooling] Validate non-negative rerank top_n frontend
#46119 opened Jun 19, 2026 by taneem-ibrahim Contributor Loading…
[ROCm][Perf] MXFP8 dense-linear + grouped-MoE GEMM optimizations for MiniMax-M3 rocm Related to AMD ROCm
#46117 opened Jun 19, 2026 by amd-ethany Loading…
1
[Core][KV-transfer] MoRIIO: flexible prefill-TP rank selection for heterogeneous TP<->DP reads documentation Improvements or additions to documentation kv-connector v1
#46116 opened Jun 18, 2026 by edwinlim0919 • Draft
2 of 4 tasks
3
[Bugfix] MoRIIO toy P/D proxy: fix DP-rank index aliasing + harden for high-concurrency bursts bug Something isn't working documentation Improvements or additions to documentation kv-connector
#46115 opened Jun 18, 2026 by edwinlim0919 Loading…
2 of 4 tasks
3
[ROCm][Bugfix] bug Something isn't working rocm Related to AMD ROCm
#46114 opened Jun 18, 2026 by micah-wil Contributor Loading…
[Bugfix] [Rust Frontend] Fix stop string truncation with repeated matches bug Something isn't working ready ONLY add when PR is ready to merge/full CI is needed rust
#46113 opened Jun 18, 2026 by reidliu41 Contributor Loading…
3 tasks
3
[Performance] Reduce update_from_output CPU overhead for decode batches performance Performance-related issues v1
#46112 opened Jun 18, 2026 by ji24077 Loading…
5 tasks done
2
[ROCm] Detect ROCm via KFD topology when amdsmi cannot enumerate GPUs rocm Related to AMD ROCm
#46110 opened Jun 18, 2026 by lhl Loading…
1
[ROCm][CI] Skip Qwen3.5-35B-A3B-MXFP4-AITER-TP2 for non gfx950 qwen Related to Qwen models ready ONLY add when PR is ready to merge/full CI is needed rocm Related to AMD ROCm
#46109 opened Jun 18, 2026 by charlifu Contributor Loading…
[Model] ColQwen3.5: fix retrieval correctness (bias + bidirectional) documentation Improvements or additions to documentation multi-modality Related to multi-modality (#4194) qwen Related to Qwen models
#46108 opened Jun 18, 2026 by athrael-soju Contributor Loading…
2
[Spec Decode] Support SWA + DFlash for MiMo qwen Related to Qwen models
#46104 opened Jun 18, 2026 by benchislett Member Loading…
ProTip! Find all pull requests that aren't related to any open issues with -linked:issue.