Skip to content

Issues: vllm-project/vllm

[Roadmap] vLLM Roadmap Q2 2025
#15735 opened Mar 29, 2025 by simon-mo
Open 8
[V1] Feedback Thread
#12568 opened Jan 30, 2025 by simon-mo
Open 87
[Roadmap] vLLM Release/CI/Performance Benchmark Q2 2025
#16284 opened Apr 8, 2025 by khluu
Open 3
Beta
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

1,688 Open 6,357 Closed
1,688 Open 6,357 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
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

[Bug]: [v0.8.4][Critical] Tools calling broken: xgrammar rejects minItems in JSON Schema, blocking agent functionality bug Something isn't working
#16880 opened Apr 19, 2025 by okamiRvS
1 task done
@russellb
[Usage]: Request scheduling when using LoRA usage How to use vllm
#16876 opened Apr 19, 2025 by chenhongyu2048
1 task done
[Bug]: KeyError in mm_input_cache when processing multimodal requests with Qwen2.5-VL-72B bug Something isn't working
#16875 opened Apr 19, 2025 by uyzhang
1 task done
2
[New Model]: jinaai/jina-embeddings-v2-base-code new-model Requests to new models
#16874 opened Apr 19, 2025 by cynial
1 task done
[Bug]: Bug while using deepspeed with TRL with vLLM bug Something isn't working
#16867 opened Apr 18, 2025 by abeerag
1 task done
[Bug]: vllm 0.8.3 abnormal TTFT (too long) in the first serving bug Something isn't working
#16858 opened Apr 18, 2025 by sjtu-zwh
1 task done
[Feature]: Support Gemma 3 QAT series feature request New feature or request
#16856 opened Apr 18, 2025 by rbavery
1 task done
[Bug]: Two BOS when using chat bug Something isn't working
#16853 opened Apr 18, 2025 by efsotr
1 task done
1
1
[Bug]: Invalid json schema disconnect the container from GPU without user notice bug Something isn't working
#16851 opened Apr 18, 2025 by Rictus
1 task done
[Bug]: Calling the load_weights method of the MOE model failed bug Something isn't working
#16842 opened Apr 18, 2025 by lyz22233
1 task done
10
[Bug]: Rocm Memory Access Fault. bug Something isn't working rocm Related to AMD ROCm
#16840 opened Apr 18, 2025 by zhang-yu-wei
1 task done
[Bug]: 0.8.3 V1 engine /completions with prompt_logprobs outputs Ġ instead of a space in decoded_token bug Something isn't working
#16838 opened Apr 18, 2025 by tripathiarpan20
1 task done
2
[Bug]: 0.8.3 V1 engine /completions breaks when prompt_logprobs set to 10; works when set between 1-9 bug Something isn't working
#16836 opened Apr 18, 2025 by tripathiarpan20
1 task done
[Bug]: PreemptionMode.RECOMPUTE is incorrect bug Something isn't working
#16832 opened Apr 18, 2025 by efsotr
1 task done
[Bug]: An error occurred when deploying DeepSeek-R1-Channel-INT8 on two A100 machines using lws bug Something isn't working
#16827 opened Apr 18, 2025 by MouseSun846
1 task done
[Bug]: The Transformers implementation of My Model is not compatible with vLLM. bug Something isn't working
#16826 opened Apr 18, 2025 by SnowCharmQ
1 task done
@hmellor
8
[Bug]: Bug in LRUEvictor: priority_queue and free_table desynchronization cause error bug Something isn't working
#16825 opened Apr 18, 2025 by loricxy0707
[Usage]: How vllm split the llm when pipeline parallel size>1, is it divided equally by the number of hidden layers? usage How to use vllm
#16822 opened Apr 18, 2025 by janelu9
1 task done
[Bug]: benchmark with mii backend occurs Error bug Something isn't working
#16821 opened Apr 18, 2025 by tishizaki
1 task done
[Feature]: suggest passing a splited tensor to RLHF vllm's load_weights when tp>1 feature request New feature or request
#16820 opened Apr 18, 2025 by janelu9
1 task done
2
[Bug]: When configuring Ray with a custom temporary directory using the --temp-dir parameter, the distributed multi-node inference cluster fails to deploy successfully. bug Something isn't working
#16819 opened Apr 18, 2025 by shalousun
[Installation]: how to add vllm[audio] when build from source code in arm64 platform installation Installation problems
#16816 opened Apr 18, 2025 by fanfan-lucky
1 task done
1
[Bug]: 0.8.4 serve QwQ-32B-AWQ failed bug Something isn't working
#16811 opened Apr 18, 2025 by hicodo
1 task done
@mgoin
[Bug]: RuntimeError: operator _C::machete_gemm does not exist bug Something isn't working
#16810 opened Apr 18, 2025 by KilJaeeun
1 task done
[Bug]: Cannot use FlashAttention-2 backend for head size 88 for serving llama4 bug Something isn't working
#16808 opened Apr 18, 2025 by zhaoclaire
1 task done
2
ProTip! Type g i on any issue or pull request to go back to the issue listing page.