sglang
https://github.com/sgl-project/sglang
Python
SGLang is a high-performance serving framework for large language models and multimodal models.
Triage Issues!
When you volunteer to triage issues, you'll receive an email each day with a link to an open issue that needs help in this project. You'll also receive instructions on how to triage issues.
Triage Docs!
Receive a documented method or class from your favorite GitHub repos in your inbox every day. If you're really pro, receive undocumented methods or classes and supercharge your commit history.
Python not yet supported1 Subscribers
Add a CodeTriage badge to sglang
Help out
- Issues
- [DO NOT MERGE] Fix prefill delayer not considering prefill in chunked scenario
- Do not trigger release workflows on main branch
- [AMD] Support symmetric memory with pynccl for AMD GPUs
- Make per‑token expert‑distribution recorder use asynchronous data syncing
- Add Qwen3-Omni to Qwen MoE architecture handling in fused_moe_triton
- Fix KeyError when loading ModelOpt FP8 checkpoint for Falcon-H1R-7B
- [Feature] Parallelize module loading to speed up server launch and refit for Diffusion models
- [PD] Add graceful RDMA shutdown for Mooncake/NIXL disaggregation connectors
- [Disagg] Gate disagg queue limit on grpc_mode
- Skip unnecessary testcases for CPU
- Docs
- Python not yet supported