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(serving): add --enable-sort-tool-schema-keys to share prefix cache across tool key orders
- [Fix] Correct inverted assertion message for enable_mixed_chunk with speculative decoding
- [PD] PP prefill: fold HiCache prefetch readiness into the bootstrap consensus
- [PD] PP prefill: ordered immutable bootstrap decisions with exactly-once apply
- [router] PD: never auto-replay a request that may already be dispatched
- [diffusion] Sparse attention backends: run the dense path on the dense backend
- [AMD][CI] Pre-build AITER JIT kernels after a forced AITER rebuild
- Fix deterministic DSV4 top-k fallback on ROCm
- Fix IndexError when reducing CPU tensors after monkey_patch_torch_red…
- fix(moe): don't crash on a2a dispatch outputs without topk_output in mxfp4 path
- Docs
- Python not yet supported