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
- [Bug] GLM 5.3 segfault on MI300 in SGLang scheduler
- [Feature] Batched asynchronous Engram host-row prefetch
- [NPU] Support host_rdma transfer protocol for PD disaggregation on A5
- fix: support FP8 E4M3 inference on SM80
- [NPU] Support DSpark static mode on GLM 5.2
- [Perf] xgrammar backend: rollback() does an O(N) list copy -> O(N^2) grammar bitmask cost under speculative decoding
- [Bugfix] Preserve NVFP4 AWQ prescaling in MLP fusion and Marlin paths
- [Perf] xgrammar: truncate accepted_tokens in place in rollback() (O(k) instead of O(N))
- [HiCache] Track HybridLinear/Mamba pipeline-parallel correctness and support
- [Benchmark] Fail requests on server-side streaming errors
- Docs
- Python not yet supported