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
- [Docs][AMD] Refresh GLM-5.3-Flash recipes for gfx942 and gfx950
- [Fix] Use a safe stop-string decode window
- [Docs][AMD] Add optimized GLM-5.3-Flash MI355X recipe
- [Bug] Models fail to produce non-empty answer while evaluated for reasoning on long context.
- [metrics] Add avg_request_queue_latency gauge for live queue-wait monitoring
- [HiCache] Wait for load-back before deferred Mamba COW
- fix(anthropic): return 400 for template-rejected effort, stop rewriting xhigh
- feat(openai): accept max_thinking_tokens on the chat completions endpoint
- fix(modelopt): expand is_layer_excluded for fused and model.-prefixed names
- [Bug] 374 MB of every `lmsysorg/sglang:latest` pull is three directories the Dockerfile deletes one layer too late
- Docs
- Python not yet supported