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
- [Fix] minimax-m2: Scope streamed parameters to the current invoke
- [Fix] dllm: Resolve LLaDA2 block size and mask ID from checkpoint metadata
- [Feature] add chat and completions to the shared v1.api protos
- [Fix] hunyuan: Skip undefined tools in streaming like detect_and_parse
- [Fix] scheduler: Keep arrival order for requests outside the running routing keys
- [Perf] diffusion quantization layer: fix 6 real perf/overhead bugs
- [Perf] diffusion quantization layer: fix 6 real perf/overhead bugs
- [Perf] diffusion: fix 6 quantization-layer overheads (NVFP4 scale conversion, W8A16, BnB, Nunchaku)
- [Feat] jit: Add SGLANG_JIT_DISABLE_FAST_MATH to drop --use_fast_math from JIT builds
- [Fix] step3: Keep tool-call parameter values that contain '<'
- Docs
- Python not yet supported