Skip to content

Issues: vllm-project/vllm

[Roadmap] vLLM Roadmap Q1 2025
#11862 opened Jan 8, 2025 by simon-mo
Open 6
[V1] Feedback Thread
#12568 opened Jan 30, 2025 by simon-mo
Open 49
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

1,390 Open 5,542 Closed
1,390 Open 5,542 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]: ChatCompletionRequest rejects its own defaults bug Something isn't working
#14351 opened Mar 6, 2025 by schoennenbeck
1 task done
1
[Performance]: The measured concurrency value is twice as high as the calculated value in the formula, why? performance Performance-related issues
#14350 opened Mar 6, 2025 by xwzheng1020
1 task done
[Bug]: vllm cannot connect to an external ray cluster bug Something isn't working
#14349 opened Mar 6, 2025 by dotbalo
1 task done
[Feature]: How can I get embedding result from images？ Can Qwen2.5-vl-7b do this? feature request New feature or request
#14348 opened Mar 6, 2025 by LwengGitHub
1 task done
[Feature]: Ovis2 VLM series feature request New feature or request
#14346 opened Mar 6, 2025 by Strand2013
1 task done
[Doc]: How can I set the date_string for the chat templates documentation Improvements or additions to documentation
#14344 opened Mar 6, 2025 by FelixNeutatzMainWebSolutions
1 task done
[Bug]: online-rl sampling is different from offline-sampling bug Something isn't working
#14341 opened Mar 6, 2025 by yyht
1 task done
distributed inference multi-node communication bug
#14340 opened Mar 6, 2025 by leo4678
[Feature]: eagle支持多模态模型 feature request New feature or request
#14337 opened Mar 6, 2025 by perdone
1 task done
[Feature]: reasoning_tokens in Chat Completion Response usage feature request New feature or request
#14335 opened Mar 6, 2025 by gaocegege
1 task done
[Bug]: GPU索引指定失败 bug Something isn't working
#14334 opened Mar 6, 2025 by hackerhaiJu
1 task done
[Bug]: vLLM returning 415 status code at high load bug Something isn't working
#14333 opened Mar 6, 2025 by chiragjn
1 task done
[Bug]: opentelemetry POC vLLM span cannot be concatenated with HTTP spans. bug Something isn't working
#14330 opened Mar 6, 2025 by RichardoMrMu
1 task done
2
[Usage]: How do I set the input image size when using qwen2-vl? usage How to use vllm
#14325 opened Mar 6, 2025 by glamourzc
1 task done
1
[Bug]: 'DeepseekV2Model' object has no attribute 'config' when enabling P/D Disaggregation bug Something isn't working
#14324 opened Mar 6, 2025 by JewelRoam
1 task done
[Usage]: What is the default input construction of multimodel input? usage How to use vllm
#14322 opened Mar 6, 2025 by DK-DARKmatter
1 task done
@ywang96
[Feature]: Invalid attention backend for cuda with TORCH_SDPA better error message feature request New feature or request
#14320 opened Mar 6, 2025 by jamesbraza
1 task done
[Doc]: Why is max block_size on CUDA 32? documentation Improvements or additions to documentation
#14319 opened Mar 5, 2025 by ptarasiewiczNV
1 task done
[Feature]: Expose a read-only API to check whether engine is sleeping feature request New feature or request
#14311 opened Mar 5, 2025 by waltforme
1 task done
1
1
Issue with Mistral Small and greek characters usage How to use vllm
#14307 opened Mar 5, 2025 by myrulezzz
1 task done
[Usage]: Logprobs Scaling with O(n) Complexity – Unexpected Performance Degradation usage How to use vllm
#14300 opened Mar 5, 2025 by Rachum-thu
1 task done
[Installation]: Attempting to build and run vLLM for Intel Core Ultra 7 155H with ARC iGPU installation Installation problems
#14295 opened Mar 5, 2025 by cgruver
1 task done
1
[New Model]: llava-onevision-qwen2-72b-ov-sft new model Requests to new models
#14290 opened Mar 5, 2025 by Song-WenPo
1 task done
1
[Feature]: Chat inputs to AsyncLLMEngine feature request New feature or request
#14289 opened Mar 5, 2025 by sfc-gh-mkrubinski
1 task done
1
[Bug][V1]: Loading Llama3.1-8B-INT8 gets OOM when using VLLM_USE_v1=1 but safe using v0 bug Something isn't working
#14286 opened Mar 5, 2025 by fahadh4ilyas
1 task done
ProTip! Updated in the last three days: updated:>2025-03-03.