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] linker: Support lmcache external linker
- [Fix] [NPU] mooncake: Pair DSV4 and MLA KV buffers by global layer ID
- [Feat] quantization: Route named layers to a second online quantization format
- [Fix] paged-experts: use libc when Python omits memfd_create
- [Fix] openai: recover Responses API logprob bytes from token ids
- [Feat] dflash: Serve MoE FFN drafts for DFlash and DSpark
- [Feat] spec/dflash: keep an all-sliding-window DFLASH draft's KV on the target's SWA slots
- [Fix] scheduler: Keep prefill batches homogeneous by input form
- [Fix] cp: Embed the full sequence when a CP hook returns no embeddings
- [Perf] weight_checker: Avoid per-chunk host syncs and redundant FP32 casts in compare_weights
- Docs
- Python not yet supported