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] Worker Snapshot Support for Recoverable KV Placement State in sgl-router
- [Bug] [Security tracking] Private advisory GHSA-8374-wrr5-7q7f has received no maintainer response
- Honor should_apply_lora when wrapping LoRA target modules
- [BUG] mxfp4 + sharded_state load format silently drops expert weights (gpt-oss-20b)
- [PD] Enforce the request waiting timeout in disaggregation mode
- [Fix] Decouple `--language-only` from encoder disaggregation
- [RFC] Agent-aware session affinity without routing keys: a router policy
- [Docs] DeepSeek-V4: switch H200 FP4 low-latency/high-throughput to flashinfer_mxfp4
- [NPU][Tracking] Ascend A5 MXFP8/MXFP4 Capability and Model Coverage
- [RFC] HIP/ROCm - Provide a bit-exact SWA prefix reuse for DeepSeek-V4 with unified_kv atten backend
- Docs
- Python not yet supported