8000 Issues · sgl-project/sglang · GitHub
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

Issues: sgl-project/sglang

Development Roadmap (2025 H1)
#4042 opened Mar 4, 2025 by zhyncs
Open 19
[Roadmap] Prefill and Decoding Disaggregation
#4655 opened Mar 21, 2025 by ByronHsu
Open 18
[Roadmap] EP Enhancement
#4734 opened Mar 24, 2025 by ch-wan
Open 6
Beta
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

506 Open 1,434 Closed
506 Open 1,434 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] CUDA OOM when DP attention enabled, maybe due to incorrect acceptable length estimation.
#6027 opened May 5, 2025 by junliu-mde
5 tasks done
1
[Bug] Unable to deploy with CPUs without AVX
#6025 opened May 5, 2025 by Quang-elec44
3 of 5 tasks
[Bug] Document is different with source of --reasoning-parser value
#6023 opened May 5, 2025 by engchina
5 tasks done
Throughput Discrepancy Between SGLang Server Logs and LLMPerf Tool for Qwen3 Models
#6022 opened May 5, 2025 by nskpro-cmd
1
Instruction for Running DeepSeek with Large-scale PD and EP collaboration deepseek
#6017 opened May 5, 2025 by fzyzcjy
@fzyzcjy @ch-wan
1
Review Request for Security Vulnerability Report
#6008 opened May 4, 2025 by kexinoh
[RFC] sm75 EOL
#6006 opened May 4, 2025 by zhyncs
3
[Bug] AttributeError: 'MHATokenToKVPoolHost' object has no attribute 'start_layer' when using --enable-hierarchical-cache
#6005 opened May 4, 2025 by Simon-Li
5 tasks done
1
3
[Bug] OutOfResources: out of resource: shared memory, Required: 196608, Hardware limit: 65536 when run deepseek-r1 on sglang 0.4.6 with AMD Mi308
#6001 opened May 4, 2025 by GuoxiangZu
5 tasks done
[Bug] Tensor model parallel group is not initialized when deploying Qwen3-30B-A3B-AWQ
#6000 opened May 4, 2025 by SecretSettler
5 tasks done
5
[Bug] importError: libharpcuda.so.0: cannot open shared object file: No such file or directory
#5999 opened May 3, 2025 by auroraontheway
1 of 5 tasks
1
[Bug] out of resource: shared memory with 0.4.6 Qwen3-30B-A3B-FP8-Dynamic
#5995 opened May 3, 2025 by bash99
5 tasks done
[Feature] high performance multi node custom all reduce high priority
#5994 opened May 3, 2025 by zhyncs
2 tasks
@Alcanderian @yizhang2077
@ispobock @zhyncs @Fridge003
[Feature] Integrate FlashMLA into sgl-kernel
#5989 opened May 3, 2025 by Fridge003
2 tasks
2
[Bug] Segmentation Fault on AMD MI300X
#5987 opened May 2, 2025 by kimbochen
5 tasks done
[Performance Tuning Help] Enabling DP Attention + JIT DeepGEMM + PyTorch Compile Underperforms Baseline
#5985 opened May 2, 2025 by kimbochen
4
[Bug] Requests with logprobs throws Internal server 500 error
#5984 opened May 2, 2025 by om6-prakash
2 of 5 tasks
[Feature] Support for tool_calls in Assistant Messages Input
#5983 opened May 2, 2025 by kibitzing
2 tasks done
[document link is broken] from main page, click installation link, it is broken
#5982 opened May 2, 2025 by gaowayne
1
[Feature] Add KV cache usage prometheus metrics
#5979 opened May 2, 2025 by jorgeantonio21
[Bug] Qwen3 14B runs very slowly on a GPU with the SM75 architecture for inference.
#5978 opened May 2, 2025 by maxin9966
5 tasks done
[Feature] Generative Score API high priority
#5973 opened May 2, 2025 by chanh
2 tasks done
[Feature] microsoft/Phi-4-multimodal-instruct help wanted Extra attention is needed high priority microsoft
#5972 opened May 2, 2025 by avinash31d
2 tasks done
@hebiao064 @zhyncs
3
[Feature] Support more multi-modal input for VLM feature
#5964 opened May 2, 2025 by JustinTong0323
2 tasks
@JustinTong0323
[Feature] support abort ongoing request high priority RLHF Using SGLang for post training
#5963 opened May 2, 2025 by zhuzilin
2 tasks done
1
@zhaochenyang20
1
ProTip! Type g i on any issue or pull request to go back to the issue listing page.
0