Skip to content

Issues: vllm-project/vllm

[RFC]: Deprecating vLLM V0
#18571 opened May 22, 2025 by WoosukKwon
Open 30
[Roadmap] vLLM Roadmap Q2 2025
#15735 opened Mar 29, 2025 by simon-mo
Open 15
[Roadmap] vLLM Release/CI/Performance Benchmark Q2 2025
#16284 opened Apr 8, 2025 by khluu
Open 3
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Clear current search query, filters, and sorts
1,012 Open 2,688 Closed
1,012 Open 2,688 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
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
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

[Bug]: KeyError: 'language_model.layers.0.self_attn.qkv_proj.weight' bug Something isn't working
#19149 opened Jun 4, 2025 by Rinnolo
1 task done
1
[Bug]: max-model-len + max-num-seqs is not reducing vram usage bug Something isn't working
#19148 opened Jun 4, 2025 by ExtReMLapin
1 task done
[Bug]: error is not a multimodal model when serving Qwen/Qwen3-8B connected to gr.load_chat(...) bug Something isn't working
#19144 opened Jun 4, 2025 by vadimkantorov
1 task done
[Bug]: Error when loading model(gemma-3-4b) merged after DeepSpeed training into vLLM bug Something isn't working
#19139 opened Jun 4, 2025 by taegyunjjang
1 task done
1
2
[Bug]: Error occurred while performing model inference using 0.8 H20s from the virtualized computing pool. bug Something isn't working
#19137 opened Jun 4, 2025 by SuperJunier666
1 task done
[Bug]: 单机多卡推理 tensor-parallel-size和pipeline-parallel-size 推理结果差距巨大 bug Something isn't working
#19136 opened Jun 4, 2025 by Kenwwww
1 task done
1
[Bug]: Qwen3 non thinking mode is much slower than thinking mode bug Something isn't working
#19124 opened Jun 4, 2025 by whulc
1 task done
[Bug]: Failed to start vLLM v1 with Ray. Encountered the following error: KeyError: 'bundles' bug Something isn't working
#19123 opened Jun 4, 2025 by Ind1x1
1 task done
3
[Bugfix] fix v1 cpu worker fails on macOS bug Something isn't working ready ONLY add when PR is ready to merge/full CI is needed
#19121 opened Jun 4, 2025 by kebe7jun Loading…
3 tasks done
1
13
[Bug]: CPU v1 worker run fails on macOS bug Something isn't working
#19120 opened Jun 4, 2025 by kebe7jun
1 task done
1
[Bugfix] Fix port handling in make_zmq_path bug Something isn't working codex ready ONLY add when PR is ready to merge/full CI is needed
#19117 opened Jun 4, 2025 by mgoin Loading…
4
[Bug]: Deepseek-R1 with DEP16 hangs after kv cache allocation bug Something isn't working
#19101 opened Jun 3, 2025 by ptarasiewiczNV
1 task done
1
[Bug]: Internal Server Error: python3 openai_chat_completion_client_for_multimodal.py -c audio when using Qwen/Qwen2-Audio-7B-Instruct bug Something isn't working
#19083 opened Jun 3, 2025 by IceForChoco
1 task done
8
[Bug]: CUDA error: unknown error when running vllm serve on WSL2 Ubuntu22.04 bug Something isn't working
#19077 opened Jun 3, 2025 by ezioasche
1 task done
[Bug]: vllm.third_party.pynvml.NVMLError_InvalidArgument: Invalid Argument bug Something isn't working
#19071 opened Jun 3, 2025 by tengdecheng
1 task done
6
[Bug]: ValueError: Attempted to assign 119 = 119 multimodal tokens to 120 placeholders bug Something isn't working
#19070 opened Jun 3, 2025 by jojolee123
1 task done
24
[Bug]: 'FutureWrapper' object has no attribute 'sampled_token_ids' when using ray to perform pipeline parallelism bug Something isn't working
#19063 opened Jun 3, 2025 by havever
1 task done
2
[Bug]: Hermes tool parser stream output error in Qwen3 case bug Something isn't working
#19056 opened Jun 3, 2025 by LiuLi1998
1 task done
1
5
[Bug]: vllm 0.9 image gives me gibberish bug Something isn't working rocm Related to AMD ROCm
#19052 opened Jun 3, 2025 by azjam78910
1
[Bug]: Quantization method specified in the model config (fp8) does not match the quantization method specified in the quantization argument (gguf). bug Something isn't working
#19050 opened Jun 3, 2025 by Minami-su
1 task done
9
[Bug]: System Memory OOM after upgrading to v0.9.0.1 bug Something isn't working
#19048 opened Jun 3, 2025 by ly0koS
1 task done
1
[Bug]: vllm profiling result contains invalid utf-8 code bug Something isn't working
#19043 opened Jun 3, 2025 by helunwencser
1 task done
4
[Bug]: 100% CPU usage when idle. While loop in acquire_read pegging the CPU. bug Something isn't working
#19036 opened Jun 2, 2025 by MathieuBordere
1 task done
5
[Bug]: Dual a6000 pros not working. Arch 120. bug Something isn't working
#19025 opened Jun 2, 2025 by vladrad
1 task done
15
[Bug]: gpu-memory-utilization does not work bug Something isn't working
#19023 opened Jun 2, 2025 by zswodegit
1 task done
4
ProTip! Add no:assignee to see everything that’s not assigned.