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
- [LoRA 07/21] Record a LoRA-free decode graph for the dense engine
- [LoRA 08/21] Absorbed-MLA kv_b corrections on the dense runner
- [LoRA 09/21] Inkling shared-sink LoRA on the dense engine
- [LoRA 10/21] MoE execution plans
- [LoRA 11/21] MoE token routes
- [LoRA 12/21] Shipped MoE plan tables for SM90 and SM100
- [LoRA 13/21] MoE LoRA stage kernels
- [LoRA 14/21] MoE base-GEMM providers and the Triton BF16 vendor
- [LoRA 15/21] MoE LoRA runner and serving integration
- [LoRA 16/21] Packed MoE schedules for the CuTeDSL GEMMs
- Docs
- Python not yet supported