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
- [Docs] Qwen3.8-Flash-Next: use a float32 SSM state for the H200 speculative cells
- test(npu): run Kimi-K3 gpqa in nightly with source build
- Fix DSA seed metadata sizing when DSA is disabled
- [HiCache] Write-through host backup for chunked prefills (#33714)
- config: validate cuda graph config values
- [MiniMax-M3][AMD] Fix EAGLE3 TARGET_VERIFY on MI300 + AITER unquant MoE
- [Scheduler] Tie overlap batch snapshot lifetime to result completion
- [Bug] FlashInfer prefill treats AttentionType.DECODER_BIDIRECTIONAL as causal
- [Qwen3.8] Support Qwen3.8-Max residue inference
- [AMD] [GLM5] Fuse the DSA indexer Q/K rope + quant + K-cache write into one aiter kernel
- Docs
- Python not yet supported