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] kv-indexer-bridge: receive event batches outside tokio's coop budget
- [Fix] Z-Image: Synchronize device after warmup request
- Qwen4-Exp (Qwen3.8-Flash-Next) QSA MTP: draft_tokens > compress ratio and topk > 1 crash late in scheduler init instead of failing arg validation
- [diffusion] comfyui: opt-in native worker batching (Z-Image, FLUX.1)
- [Fix] offloader: Preserve cached weights during CPU offload
- [Feat] moe: Allow SiTU on the CuTe DSL NVFP4 MoE (Kimi-K3 W4A16)
- [Feat] score/embedding: Add normalize flag, score rid tracing, embed-override validation, Qwen cls head fix, and scheduler observability
- [Perf] custom_op: Call register_custom_op ops directly in plain eager execution
- [Fix] benchmark: Compensate cumulative request arrival drift
- [Feature] Could you include the sgl-model-gateway container image alongside each version release?
- Docs
- Python not yet supported