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] diffusion/pi05: Honor request seeds for action noise
- [Perf] fla: let fused_recurrent_kda update the state pool in place
- [Bug] Decode HiCache restore returns HTTP 500 under host-cache pressure with GLM-5.3-Flash
- [Feat] linker: Support async lookup in prefetch mode
- [Feat] dflash: Support sliding-window draft KV pools for NIXL PD
- [Fix] distributed: Isolate local SHM writer ports by rank
- [CI] [AMD] ci: Run 16 kernel tests per PR on AMD, as CUDA does
- [Feat] simulator: Simulate prefill-decode disaggregation with modelled KV transfer
- [Perf] [AMD] kimi-k3: Write the fp8-Q asm verify query in the fused Q/cache launch
- [Fix] disaggregation: Make CommonKVReceiver._clear() idempotent under early allocation
- Docs
- Python not yet supported