Skip to content

Issues: vllm-project/vllm

[Roadmap] vLLM Roadmap Q1 2025
#11862 opened Jan 8, 2025 by simon-mo
Open
vLLM's V1 Engine Architecture
#8779 opened Sep 24, 2024 by simon-mo
Open 9
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

1,193 Open 4,711 Closed
1,193 Open 4,711 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]: Deepseek-v3 performace on benchmark didn't match with paper bug Something isn't working
#11971 opened Jan 12, 2025 by jongjyh
1 task done
[Feature]: Support Phi-4 GGUF feature request
#11970 opened Jan 12, 2025 by felix068
1 task done
1
1
[New Model]: Cosmos-1.0-Autoregressive (World Foundation Models) new model Requests to new models
#11968 opened Jan 12, 2025 by Haoxiang-Wang
1 task done
[Doc]: Invalid JSON examples in Engine Args Document documentation Improvements or additions to documentation good first issue Good for newcomers help wanted Extra attention is needed
#11965 opened Jan 12, 2025 by ardapekis
1 task done
[Feature]: 【support tts llm like cosyvoice2.0】 feature request
#11964 opened Jan 12, 2025 by wang-TJ-20
1 task done
[Bug]: failure when compiling httptools bug Something isn't working
#11961 opened Jan 11, 2025 by gnusupport
1 task done
[Usage]: How to reach 100% GPU Compute Utilization ? usage How to use vllm
#11959 opened Jan 11, 2025 by MohamedAliRashad
1 task done
[Bug]: How to run LanguageBind/Video-LLaVA-7B-hf bug Something isn't working
#11954 opened Jan 11, 2025 by jianghuyihei
1 task done
1
[Bug]: The random seed behavior when loading a model in vLLM is confusing. bug Something isn't working
#11953 opened Jan 11, 2025 by Aratako
1 task done
[Feature]: Support for serving two llms at the same time feature request
#11950 opened Jan 11, 2025 by czg1225
1 task done
[RFC]: Pipeline-Parallelism for vLLM V1 RFC
#11945 opened Jan 10, 2025 by ruisearch42
1 task done
@youkaichao
[Feature] [Spec Decode]: Simplify the Use of Eagle Spec Decode feature request
#11943 opened Jan 10, 2025 by LiuXiaoxuanPKU
1 task done
[Bug]: Loading model from S3 using RunAI Model Streamer excludes too many files bug Something isn't working
#11929 opened Jan 10, 2025 by svantesorberg
1 task done
1
[Feature]: Support out-of-tree register of customize quantization method feature request
#11926 opened Jan 10, 2025 by ice-tong
1 task done
1
[Usage]: Multi-Step Scheduling with Speculative Decoding usage How to use vllm
#11917 opened Jan 10, 2025 by ynwang007
1 task done
[Usage]: Compilation and Execution Issues Across Different GPU Models After Modifying vLLM Source Code usage How to use vllm
#11914 opened Jan 10, 2025 by Yang1032
1 task done
[Bug]: deepseek-v3-bf16 only generates a null char ""! bug Something isn't working
#11913 opened Jan 10, 2025 by janelu9
1 task done
[Performance]: Performance regression for long prompt length since vLLM0.6.4.post1 performance Performance-related issues
#11912 opened Jan 10, 2025 by hustxiayang
1 task done
[Bug]: LLAMA3.1 output not matching with HuggingFace when beam search is enabled. bug Something isn't working
#11911 opened Jan 10, 2025 by pratcooper
1 task done
[Bug]: python offline_inference_whisper.py example issue bug Something isn't working
#11909 opened Jan 10, 2025 by silvacarl2
1 task done
2
[RFC]: Implement Structured Output support for V1 engine RFC
#11908 opened Jan 9, 2025 by russellb
1 task done
[Feature]: Support Multiple Tasks Per Model feature request
#11905 opened Jan 9, 2025 by FurtherAI
1 task done
[Bug]: example/openai_chat_completion_client_with_tools.py not working bug Something isn't working
#11903 opened Jan 9, 2025 by Hurricane31337
1 task done
5
[Bug]: Problems with releasing memory after starting the vllm container bug Something isn't working
#11902 opened Jan 9, 2025 by JohnConnor123
1 task done
[Bug]: VLLM get stucks with Qwen VL 7B bug Something isn't working
#11899 opened Jan 9, 2025 by engleccma
1 task done
4
ProTip! Add no:assignee to see everything that’s not assigned.