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
- [PD] mori: support DCP KV relayout in the moriio transfer backend
- Fix reasoning parser finalization in Responses streams
- [dLLM] Run several denoise forwards per scheduled FDFO round
- [Bugfix] Fix causal sliding-window attention in MiMo audio tokenizer
- [Fix] Align prefill CUDA graph token buckets with attention TP size
- Dump requests sample fraction
- [rust-server] bump hf-hub to 1.0 so the tokenizer cache lookup honors HUGGINGFACE_HUB_CACHE
- [sglang-miles] Fix LoRA usage-counter lifecycle across cleanup paths
- [Scheduler] Dev-only --debug-mode: survive a failed batch instead of the process
- [Bug] DeepSeekV4TokenToKVPool (SWA/HiSparse) has no get_cpu_copy() → decode-mode retract crashes with NotImplementedError (offload is unconditional, not gated on --disaggregation-decode-enable-offload-kvcache)
- Docs
- Python not yet supported