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
- feat(qwen4): stream PLE embeddings from NVMe
- [Bug] ModelOpt FP4: is_layer_excluded misses fused module names and model.-prefixed names — mixed-precision NVFP4 checkpoints crash at load (GLM-5.3-Flash)
- [Bug] deepseek_nextn hardcodes quant_config=None for modelopt_fp4 — breaks quantized NextN drafts (GLM-5.3-Flash NVFP4 speculative decoding)
- [AMD] Support Qwen3.8-Flash-Next MXFP4 on ROCm
- [Feature] Expose opt-in per-request metrics in OpenAI-compatible responses
- [Fix] minimax-m2: streaming tool calls are lost and markers leak into content
- [Bug] Anthropic endpoint: output_config.effort forwarded unvalidated -> 500, and xhigh is made unreachable
- [Bugfix] Preserve Anthropic xhigh reasoning effort
- [Bugfix] Load BF16 MTP weights in Qwen3.5/3.8 MXFP4 compressed-tensors checkpoints
- [Qwen 3.8 Flash Next] Add sm120 (RTX PRO 6000 Blackwell) support
- Docs
- Python not yet supported