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
- [AMD] Add FlyDSL GDN prefill backend
- [NPU][HiCache] Support DeepSeek V4 L3 with MemCache
- Add opt-in CUDA event pool for hot-path wait_stream calls
- [Kimi-K3] Guard optimized paths by platform
- [Feature][DeepSeek-V4.1] Decode graph width is pinned to --context-length; add a decode-phase max_seq_len
- [Bug][function_call] Keep qwen3_coder non-streaming text after tool calls
- [NVIDIA][MegaMoE] Fix the default spec decoding moe backend when the target model uses flashinfer megamoe
- [AMD] Fix Quark block-FP8 loading in DeepSeek loader
- [Bug] Severe repetition and degenerate loops in reasoning/output when serving GLM-5.3 with DFLASH speculative decoding
- [Bugfix] Flush pending tool calls at end of stream in the Llama 3.2 detector
- Docs
- Python not yet supported