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
- [Test] Lower the SM120 NVFP4 KV GSM8K threshold to 0.60
- [Speculative Decoding] Support Adaptive Speculative Decoding with Pipeline Parallelism
- [Benchmark] Include per-request E2E latency in output details
- fix: bind delayed HTTP abort cleanup to request generation
- [Fix] Read TensorCast's WORLD placement under its current names
- [Fix] State the configured MoE-DP width in the weight-cache fingerprint
- [Fix] Shard MoE WNA16 and Quark INT4-FP8 weights by the MoE placement
- [Fix] Pass the draft's attention ownership to DFLASH's eager LiLiCorr scope
- [Fix] Size the prefill delayer's gather buffer to its TP group
- [Fix] Make the Solar model constructible and runnable
- Docs
- Python not yet supported