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
- Add assertion for abnormal input id range
- Add the Nvidia-ModelOPT FP8 & FP4 quantization test case
- [VLM] process MM data when enable_tokenizer_batch_encode is enabled
- [Scheduler] Add target batch gate for profiling
- [feat] Reduce GPU memory usage in DP vision encoder
- feat: Add C++ native tree traversal for speculative decoding with xgrammar
- [WIP][VLM] Support Eagle2_5_VL
- [perf] optimize moe_fused_gate kernel
- [Feature] Distributed Weight Data Parallelism (DWDP) for Sparse MoE Models
- [SpecActor] Decoupled speculative decoding to accelerate offline inference and RL rollout
- Docs
- Python not yet supported