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 14
[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

437 Open 1,169 Closed
437 Open 1,169 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] Docker image v0.4.4.post3-cu125 is labeled as CUDA 12.5 (cu125), but it actually contains CUDA 12.4.
#4952 opened Mar 31, 2025 by cynial
5 tasks done
Issue when running latest Mistral model
#4948 opened Mar 31, 2025 by fciannella
NotImplementedError: Updating weights_map with disk offloading is not implemented yet
#4945 opened Mar 31, 2025 by Gusha-nye
[Feature] use different lib so for fa3 in sgl-kernel high priority
#4941 opened Mar 31, 2025 by zhyncs
2 tasks
@yinfan98 @zhyncs @sleepcoo
1
[Feature] Support Video for Qwen VL
#4940 opened Mar 31, 2025 by remichu-ai
2 tasks done
[Bug] 0.0.0.0 host not supported bug Something isn't working
#4935 opened Mar 30, 2025 by gyin94
2 of 5 tasks
1
@kebe7jun
2
[Bug] Qwen/Qwen2.5-VL-7B-Instruct-AWQ sglang response time longer
#4916 opened Mar 30, 2025 by bao231
5 tasks
19
[Bug] Remove stream sync in fast decode plan of flashinfer mla backend bug Something isn't working flashinfer
#4905 opened Mar 29, 2025 by Fridge003
5 tasks
@Fridge003
[Feature] The performance fails to meet expectations.
#4903 opened Mar 29, 2025 by bebilli
2 tasks done
2
[Bug] Missing Torch and GGUF dependency in v0.4.4.post3 in Docker image
#4900 opened Mar 29, 2025 by davidsyoung
5 tasks done
1
[Bug] gemma-3-27b-it-bnb-4bit crash
#4897 opened Mar 29, 2025 by bebilli
5 tasks done
3
[Feature]about support gguf
#4894 opened Mar 29, 2025 by bebilli
2 tasks done
1
[Bug] Potential Issue with Querying Log Probabilities high priority
#4892 opened Mar 29, 2025 by yangky11
5 tasks done
@merrymercy
[Track] remove srt docker image
#4881 opened Mar 29, 2025 by zhyncs
@zhyncs
1
[Bug] zmq.error.ZMQError: Cannot assign requested address (addr='tcp://addr:port')
#4877 opened Mar 29, 2025 by HoyTiger
5 tasks done
1
[Bug] Logprobs overflow to -3.4e+38 bug Something isn't working
#4876 opened Mar 29, 2025 by zhc7
5 tasks done
@Qiaolin-Yu
Add Docs about attention backend, maybe we need to add a comprehensive one with Support Matrix such as:
#4865 opened Mar 28, 2025 by hebiao064
3
[Bug] Executing Qwen2.5-Omni-7B on SGLang 0.4.4 post2: AttributeError: 'Qwen2_5OmniConfig' object has no attribute 'hidden_size'
#4862 opened Mar 28, 2025 by didier-durand
4 of 5 tasks
3
Deployment of DeepseekV3 on 2*H100 nodes is getting stuck.
#4857 opened Mar 28, 2025 by abhay-tih
@fzyzcjy
2
[Bug] Run DeepSeek-v3-0324 on 2xH20 encountered cuda illegal memory access
#4856 opened Mar 28, 2025 by cscyuge
5 tasks done
7
Inquiry Regarding Qwen2.5-Omni Support in SGLang
#4854 opened Mar 28, 2025 by sdecoder
2
[Bug] NameError: name 'CompressedTensorsW8A16Fp8' is not defined
#4851 opened Mar 28, 2025 by vhain
5 tasks done
1
7
[Bug] DP attention with Eagle worker raises AttributeError
#4847 opened Mar 28, 2025 by knukiban
5 tasks done
1
[Feature] Mooncake CPP (Chunked Pipeline Parallelism)
#4842 opened Mar 28, 2025 by kingzevin
2 tasks done
[Bug] Multiple concurrency causes service exceptions - Qwen2.5-VL-3B-Instruct
#4838 opened Mar 28, 2025 by fz5400
5 tasks done
1
ProTip! Updated in the last three days: updated:>2025-03-28.