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 unsigned 32-bit rotation in Murmur sampling hash
- [Spec] Bundle DFlash draft KV with Mamba checkpoints
- [Fix][VLM] Enable local SHM with skip_tokenizer_init
- fix: preserve tree-owned FULL KV pages when DSV4 requests finish
- [Perf] unified_cache: Skip write-through of pages the external linker just loaded
- Fix DSA skip-topk pipeline handoff for owed outputs
- Add Hopper CuTe DSL DualGEMM SwiGLU kernel
- [NPU] Skip fused gmm1 for situ activation in Ascend runner
- [ROCm][Perf] Qwen3.5: online MXFP4 for the BF16 GDN in_proj_qkvz and out_proj
- [Spec][Bugfix] Fix EAGLE3 draft lm_head when a reduced vocab is tied
- Docs
- Python not yet supported