Skip to content

Issues: sgl-project/sglang

Development Roadmap (2024 Q4)
#1487 opened Sep 21, 2024 by Ying1123
Open 22
[Feature] DeepSeek V3 optimization
#2591 opened Dec 26, 2024 by zhyncs
Open 21
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

208 Open 754 Closed
208 Open 754 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

[Feature] Improve Multi-node recipe to run inference deepseek help wanted Extra attention is needed
#3206 opened Jan 29, 2025 by vabatista
2 tasks
@zhaochenyang20
[Bug] CUDA error: uncorrectable ECC error encountered deepseek
#3204 opened Jan 29, 2025 by HuanzhiMao
5 tasks done
@zhaochenyang20
1
[Bug] min_p_sampling_from_probs() related crashes
#3201 opened Jan 29, 2025 by zifeitong
5 tasks done
1
[Bug] Tried to run DeepSeek V3 by amd instructions
#3200 opened Jan 28, 2025 by Vladimir-A
5 tasks done
1
[Bug] constant errors + hangs using sglang + deepseek v3 (httpcore.RemoteProtocolError: peer closed connection without sending complete message body (incomplete chunked read)) deepseek help wanted Extra attention is needed
#3198 opened Jan 28, 2025 by pseudotensor
5 tasks done
@zhaochenyang20
1
[Feature] deepseek v3 60 tokens/sec on deepseek API vs. 13 tokens/sec on sglang help wanted Extra attention is needed
#3196 opened Jan 28, 2025 by pseudotensor
2 tasks done
@zhaochenyang20
2
[Feature] Support DeepSeek Janus Models help wanted Extra attention is needed visIon-LM
#3195 opened Jan 28, 2025 by juliancoy
2 tasks done
@zhaochenyang20
1
[Bug] ERROR: No matching distribution found for vllm==0.6.3.post2.dev1; extra == "srt-hip" amd
#3189 opened Jan 28, 2025 by pseudotensor
5 tasks done
@zhaochenyang20
8
Any benchmarks comparing with TGI? help wanted Extra attention is needed
#3188 opened Jan 27, 2025 by ismael-dm
@zhaochenyang20
2
[Feature] Step-by-Step Guide to Use SGLang on NVIDIA Jetson Orin platform documentation Improvements or additions to documentation good first issue Good for newcomers
#3182 opened Jan 27, 2025 by shahizat
2 tasks
@zhaochenyang20
4
[Feature] Rewrite Sampling Parameter documentation Improvements or additions to documentation good first issue Good for newcomers
#3165 opened Jan 27, 2025 by zhaochenyang20
2 tasks
@zhaochenyang20
1
[Feature] fix docs in Streaming-Synchronous-Generation documentation Improvements or additions to documentation good first issue Good for newcomers
#3164 opened Jan 27, 2025 by zhaochenyang20
2 tasks
@zhaochenyang20
1
[Feature] Reduce docs CI time good first issue Good for newcomers high priority
#3163 opened Jan 27, 2025 by zhaochenyang20
2 tasks done
@zhaochenyang20
[Feature] Remove Redundent CI of Docs good first issue Good for newcomers
#3160 opened Jan 27, 2025 by zhaochenyang20
2 tasks done
@zhaochenyang20
[Feature] Support new Qwen Models good first issue Good for newcomers
#3159 opened Jan 27, 2025 by zhaochenyang20
2 tasks done
@zhaochenyang20
[Feature] Split Docs CI good first issue Good for newcomers
#3158 opened Jan 27, 2025 by zhaochenyang20
2 tasks done
@zhaochenyang20
[Feature] Accuracy test of VLM good first issue Good for newcomers help wanted Extra attention is needed high priority visIon-LM
#3142 opened Jan 26, 2025 by zhaochenyang20
2 tasks
@zhaochenyang20
2
[Feature] Vision LM accuracy test
#3141 opened Jan 26, 2025 by zhaochenyang20
2 tasks
@zhaochenyang20
[Feature] GGUF Q4KM(4bit) format for deepseek R1 support
#3140 opened Jan 26, 2025 by wuyaoxuehun
2 tasks done
[Feature] Star attention support
#3131 opened Jan 25, 2025 by shimizust
2 tasks done
2
[Bug] Service crashed with 4 H100s and QPS=25
#3112 opened Jan 24, 2025 by yh-yao
5 tasks done
3
[Bug] Crash special token xgrammar help wanted Extra attention is needed
#3108 opened Jan 24, 2025 by maximegmd
5 tasks done
@zhaochenyang20
3
Batch inference over multiple nodes
#3103 opened Jan 24, 2025 by boyang-nlp
1
[Bug] Multi-node BUG help wanted Extra attention is needed
#3099 opened Jan 24, 2025 by sitabulaixizawaluduo
5 tasks done
@zhaochenyang20
1
[Bug] Qwen2-VL Online Serving Issue
#3098 opened Jan 24, 2025 by ywang96
5 tasks done
@yizhang2077
3
ProTip! Mix and match filters to narrow down what you’re looking for.