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
- [Perf] [AMD] dsa: Enable the gfx950 fused DSA indexer for block-FP8 wq_b/wk
- [Fix] mem_cache: charge the req_to_token table in the pre-capture KV budget
- [diffusion] Resolve FastH3 AdaLN cache variant when unset
- [Kernel] Tune GLM-5-Next fused MoE with its fused shared expert and add an RTX PRO 6000 FP8 config
- [MLX] Fix numerical stability of output logprobs
- [Roadmap] PD Disaggregation Layerwise KV Transfer
- [Perf] GGUF: llama.cpp's int8 tensor-core MMQ behind ggml_mul_mat_a8
- Handle optional usage in OpenAI frontend streams
- [diffusion] Reject unservable LLaDA-Image edits at request validation
- [diffusion] Add the LLaDA-Image cookbook
- Docs
- Python not yet supported