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
- [diffusion][ROCm][Perf]: Set gfx942 AITER FMHA rounding mode to rtz instead of rtna
- [diffusion] Continuous batching v0
- [DO NOT LAND][DESIGN] Rust Unified Radix Cache
- [router] Add tokenization hot-path benchmark
- [Platform] Fix OOT platform entry point hint
- [attention] decouple TRTLLM MHA backends from FlashInfer inheritance
- [BugFix] Fix multi-tokenizer-mode metric accounting (http_responses_total + aborted requests)
- [ci] Add DSV4 NVFP4 tests
- Add FlashInfer W4AFP8 MoE path
- observability: add tokenizer event-loop-lag metric
- Docs
- Python not yet supported