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
- [AMD] Restore DeepSeek-V4 DSpark token acceptance
- feat: add MiniCPM4.1 SparDA forecast selection
- weight-cache: support post-load lifecycle and MXFP4 IPC
- [DeepSeek V2/V3，GLM5.2] PD Disaggregation Layerwise KV Transfer & PP Early Release KV
- [RFC] Gluon MegaMoE: SGLang Integration and Multi-Node Support
- fix(npu-graph): allow text-only decode with uniformly-zero encoder_lens
- fix(npu-mrope): use triton fused kernel for sectioned multimodal prompts in forward_npu
- fix(npu-sdpa): apply cross_attention_custom_mask in ascend torch-native sdpa backend
- Validate ASR chunking progress constraints
- [Bug] compressed-tensors checkpoint + NEXTN/MTP head fails at construction with "No compressed-tensors compatible scheme was found" unless mtp.* is in `ignore` (module not named in the error)
- Docs
- Python not yet supported