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
- [sgl-router] Rewrite POLICY_DESIGN.md as a layered reference for reorg routing
- [Feature] Add public, non-fatal weight update refusal
- [Spec] Kimi-K3 EAGLE3 MLA draft under DCP + HiCache: draft routing, aux capture, physical draft KV pools
- [Perf] mem_cache: Batch the KV release of requests that finish in the same step
- [Feature] Add public weight offloader factory and post-load hook
- [Fix] Preserve Kimi K3 pipeline graph bank inputs and bound chunk profiling
- [Refactor] Separate layer boundary stage declarations
- [Refactor] Separate layer boundary connection resolution
- [Refactor] Give layer stack assembly its own boundary module
- [sgl-router] Render Kimi-K3 through sglang-processor
- Docs
- Python not yet supported