Skip to content

Issues: sgl-project/sglang

Development Roadmap (2025 H1)
#4042 opened Mar 4, 2025 by zhyncs
Open 8
[Roadmap] Prefill and Decoding Disaggregation
#4655 opened Mar 21, 2025 by ByronHsu
Open 10
[Roadmap] DeepEP Support
#4734 opened Mar 24, 2025 by ch-wan
Open 2
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

433 Open 1,142 Closed
433 Open 1,142 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] compressed_tensors requirement missing in new 0.4.4.post2 release
#4818 opened Mar 27, 2025 by ocss884
5 tasks done
1
about DP scheduler
#4816 opened Mar 27, 2025 by MuYu-zhi
1
[Bug] CustomAllreduce can not work on 4090
#4814 opened Mar 27, 2025 by kebe7jun
5 tasks done
1
@kebe7jun
[Bug] sglang[all]>=0.4.4.post2 installation environment is very confusing
#4812 opened Mar 27, 2025 by 17Reset
5 tasks done
2
[Feature] deepseek-ai/DeepSeek-V3-0324 NextN ckpt
#4808 opened Mar 27, 2025 by zhyncs
2 tasks
@ispobock
2
[Bug] The Gemma 3 model generates garbage on long generations
#4807 opened Mar 27, 2025 by Swipe4057
4 of 5 tasks
@yizhang2077 @mickqian
[Feature] VLM performance optimization high priority performance
#4805 opened Mar 27, 2025 by zhyncs
2 tasks
@yizhang2077 @mickqian
1
[feature] how to use save_sharded_state.py for use two nodes model
#4803 opened Mar 27, 2025 by diggle001
2 tasks
[Bug] an error when run the static benchmark with MTP
#4801 opened Mar 27, 2025 by yuqie
2 of 5 tasks
[Feature] Support openai responses API interface
#4793 opened Mar 26, 2025 by ron1x1-abba
2 tasks done
[Bug] gemma-3-27b-it-bnb-4bit Running failed
#4787 opened Mar 26, 2025 by chunxingque
2 of 5 tasks
The speed difference between Qwen2-VL and Qwen2.5 is very large
#4786 opened Mar 26, 2025 by tingyuyan
1
ValueError: '<class 'sglang.srt.configs.qwen2_5_vl_config.Qwen2_5_VLConfig'>' is already used by a Transformers model.
#4785 opened Mar 26, 2025 by ujjwal0005
1 of 5 tasks
2
[Bug] DP + MTP init failed with deepseek r1
#4783 opened Mar 26, 2025 by kingkingleeljj
5 tasks
[Bug] Master node didn't detect worker node not functional, requests hang until timeout
#4780 opened Mar 26, 2025 by junliu-mde
4 of 5 tasks
8
[Bug] ImportError: libcuda.so.1: cannot open shared object file: No such file or directory
#4778 opened Mar 26, 2025 by githust66
5 tasks done
2
[Feature] adopt trt llm fp8_blockscale_gemm high priority
#4776 opened Mar 26, 2025 by zhyncs
2 tasks
@yizhang2077 @zhyncs @Fridge003
[Bug] Random output when using image input with https://huggingface.co/Qwen/Qwen2.5-VL-7B-Instruct
#4774 opened Mar 25, 2025 by atbe
5 tasks done
@mickqian
1
[Feature] speedup DeepGEMM JIT compilation performance
#4773 opened Mar 25, 2025 by zhyncs
2 tasks
@zhyncs
[Bug] Extraneous/incorrect outputs when using response_format on DeepSeek models and MTP
#4771 opened Mar 25, 2025 by jondurbin
5 tasks done
@Fridge003
4
Facing issues in deploying deepseek on multinode setup
#4766 opened Mar 25, 2025 by abhay-tih
1
[Bug] DP + TP support
#4765 opened Mar 25, 2025 by JoeyYoung
[Feature] RemoteModelLoader should support pull sharded model
#4762 opened Mar 25, 2025 by AllenXu93
2 tasks done
[Bug]Throughput decreases after using speculative sampling
#4759 opened Mar 25, 2025 by bitbooboo
4 of 5 tasks
2
[Bug] GGUF model with architecture deepseek2 is not supported yet
#4756 opened Mar 25, 2025 by ciaoyizhen
5 tasks done
ProTip! no:milestone will show everything without a milestone.