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
- [DeepSeek] Write the MLA latent cache through store_mla on out-of-tree platforms
- [Feat] fpm: Retain captured intervals and support multiple FpmTiming listeners
- [Perf] sampling: Avoid full-prompt copies in custom thinking budget and n-gram logit processors
- Llama KV scale loader replaces tensor scales with floats and leaves host mirrors stale
- [Feature][Spec Decode] Add DSpine adjacent-causal-injection drafts
- [CI] [AMD] start-container: Let PR jobs use a cached image up to 2 days old
- [DeepSeek-V4.1] Extend remaining fusion batch limits to 1024 rows
- [Fix] model-loader: Preserve KV cache scale tensors
- [AMD] muse-spark: ROCm day0
- [Fix] function_call: Preserve JSON array tool calls across inter-call whitespace
- Docs
- Python not yet supported