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
- fix: reject scalar bootstrap_room whose fan-out would overflow i64
- glm4_moe_lite: skip model-side routed scaling on XPU (fix GLM-4.7-Flash accuracy)
- [router] Disable reqwest's default 30 s TCP_USER_TIMEOUT on upstream sockets
- [DSpark] Draft the proposal through one `run_draft_proposal` for the graph tail and eager
- [Bench] Apply the ITL convention uniformly across backends and label it
- [Test] Record per-step scheduling traces in the scripted runtime
- [Scheduler] Answer request-holder questions through named queries
- [Scheduler] Commit step results through an in-flight step queue
- [Scheduler] Run the pipeline micro-batch ring on the in-flight step queue
- [Scheduler] Split next-batch planning into named stages
- Docs
- Python not yet supported