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] gemma4: Support encoder-free text serving
- [Fix] request_logger: truncate list elements in --log-requests output
- [Fix] hicache: Require admin API key for POST /storage-backend/clear
- [Bug] Client-declared mm_hashes controls multimodal prefix-cache identity: wrong-image KV reuse and cross-tenant image disclosure
- [Perf] HiCache Throughput Loss Analysis in Long-Context MLA Workloads
- [Fix] minimax_h3: Support out-of-tree platforms
- [Bug] DeepSeek-V4 BF16 checkpoint is routed to the MXFP4 expert path and fails in fused MoE
- [CI] base-b: Move server tests that pass on the 5090 to 1-gpu-small
- [CI] base-b: Move kernel and unit tests that pass on the 5090 to 1-gpu-small
- [Perf] multimodal: Copy features into shared memory off the event loop
- Docs
- Python not yet supported