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
- [Diffusion][XPU] Enable the packed Ulysses QKV all-to-all on XPU
- [Bug] HiCache staged write-back: the 128 KiB batch path passes registered host VAs to cudaMemcpyBatchAsync and faults where CanUseHostPointerForRegisteredMem == 0
- [Model] Parse MTP layer index prefix-agnostically in glm5_next
- [Diffusion] Release A2A staging buffers at request boundaries
- [NPU] Avoid FP8 dispatch for INT8 MoE on A5
- [diffusion] Fix the load duration missing from subclassed server tests
- [NPU] Fuse DeepSeek-V4 decode compression metadata updates
- [Bug] Kimi-K3 EP32: severe repetition and accuracy regression with MegaMoE, not observed with DeepEP
- Fix the mapping between the TP and the given NUMA nodes.
- [DSv4.1] Support SM90 candidate indexers
- Docs
- Python not yet supported