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
- [PD] Make request role and state-transfer shape explicit
- [DCP] Drop symm-mem under DCP on NCCL older than 2.30.7
- [AMD] Clamp SwiGLU gate/up on HIP in the Triton MoE runner
- [Feature] LoRA adapter support for Dspark speculative decoding draft models
- fix(openai): preserve prompt cache keys in responses
- [Fix] kimi_k2: infer the tool name for client-style tool_call_ids instead of dropping the call
- perf(hisparse): resolve MTP KV on demand inside FlashMLA
- [ROCm][DSA] Add AITER top-k backend
- [Feature] Serve Qwen3.8-Flash-Next (176B / 6B-active MoE) at 2.57 bpw on one 24 GB GPU with 32 GB host RAM
- fix(qwen4): CPU-offload correctness, breakable graphs, mmap PLE table
- Docs
- Python not yet supported