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
- [Refactor] multimodal: [sglang-miles] [MM refactor 2/9] Initialize multimodal processors from a processor config
- [Perf] Support prompt-only hybrid cache tracking
- [CI] [AMD] monokernels: Bump the sgl-amd-mono pin daily
- [Fix] kimi-k3: Enable SiTU in FlashInfer CuTe DSL MoE
- [CI] [AMD] test: Register 36 portable unit tests for AMD CI
- [Feat] [AMD] minimax: Support MiniMax-M3.1-Flash on MI350X / MI355X (gfx950)
- [Perf] [AMD] minimax: decode indexer CP for DSpark verify on the NVFP4 index cache
- [Perf] score: Binary-search anchor positions in _anchor_counts_per_item
- [Perf] mem_cache: Avoid full free-hole sort and extent rebuild in UnifiedHostPageEnvelope
- [Fix] hicache: Restore sidecars to every Mamba destination
- Docs
- Python not yet supported