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
- [Feat] sampling: Add per-request SynthID Text watermarking
- [Refactor] moe: simplify FlashInfer MegaMoE autotune handoff
- [Refactor] sgl-kernel: Drop FlashMLA from the build
- [CI] lora: Simplify LoRA tests and add a lora rerun group
- [Fix] dumper: evaluate filters with a safe AST evaluator (no eval RCE)
- [Fix] openai: enable xgrammar reasoning when thinking mode is active
- [Feat] [NPU] diffusion: Add MindIE-SD quantized attention backend
- [Feature] Mixed ChunkPrefill Optimization Roadmap
- [Feat] metrics: Add --enable-prefix-cache-hit-rate-window for a sliding-window prefix cache hit rate
- [Fix] multimodal-gen-test: diffusion: give the native-encoder restoration test a single-process model-parallel group
- Docs
- Python not yet supported