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
- [Perf] scheduler: Send the per-request output stats only when they may have changed
- [Chore] deps: Bump transformers to 5.22.0
- [Perf] [AMD] dsv4: Speed up the gfx950 swap-AB decode attention
- [Fix] state_capturer: Prevent routed-expert capture overflow during unchunked prefill
- [Perf] linear-attn: Build the verify valid-row mask only when PP stable rows are on
- [Feat] Mistral-Large-4: add model support
- [Fix] rust-server: Fix the metrics flush race and the default-priority label
- [CI] [PPU] slash-command: Register PPU with shared opt-in CI tiers
- [Refactor] [NPU] quant: Refactor shared quantization utilities and DSpark weight mapping
- [Perf] [NVIDIA] muse-spark: Add B200 runtime optimizations
- Docs
- Python not yet supported