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(mem_cache): add KVFlow workflow-aware prefix-cache eviction
- [Bug] deepseek v4 flash 0731版本启动失败
- [Feature] Support B12X NVFP4 W4A16 (bf16 activations) MoE GEMM on SM120
- Fix multi-detokenizer routing: key on rid, not http_worker_ipc
- docs(cookbook): MiniMax-M3 re-bench on sglang 0.5.16 + config reconciliation
- [Bug] NIXL P/D stops serving after one role is replaced
- feat: expose O(1) session radix cache pressure metrics
- Fix context-boundary max_new_tokens clipping
- [Diffusion][cpu] Add diffusion rotary embedding kernel for CPU
- [DSV4] Support dsv4 decode TBO with deepep backend
- Docs
- Python not yet supported