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
- [Bug] GLM-V (glm4v processor): stray multimodal placeholder strings in message text cause 500 "Mismatch: More IMAGE tokens found than corresponding data provided"
- [Bug] Spark2.5 attention output gate hardcodes sigmoid, ignores config gate_attn_act_mode
- [Model Loader] Auto-enable checkpoint prefetch on network filesystems (NFS/Lustre)
- feat(eplb): add topology-aware expert placement
- [FIX]fix kv cache OOM on xpu
- [Feature] Dynamic Prefill Context Parallelism
- Fix OTel tracing context lost in multi-tokenizer router processes
- [Parser] Support LLM-jp-4 with GPT-OSS reasoning and tool-call parsers
- fix(function-call): publish DeepSeek V4 calls atomically
- TP2 hang with HiCache, breakable prefill CUDA graphs, and FlashInfer MNNVL on B300
- Docs
- Python not yet supported