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
- [Feat] frontend: Support X-Priority and RFC 9218 Priority headers
- [Doc] server_args: --mem-fraction-static is a fraction of free memory at startup
- [Bug] SGLang FlexKV Exposes Tenant and LoRA KV Cache Across Namespaces
- [Feat] openai: Support DSV4.1 dynamic tools in Responses and Messages
- [Fix] rust-server: Keep the /v1/loads snapshot lock wait off the async workers
- [Bug] [AMD gfx12] HIP custom all-reduce 1-stage gives wrong, rank-divergent sums over PCIe (2x R9700): relaxed start flag
- [Perf] server_args: leave the ModelConfig memo out of a pickled record
- [Feat] linker: Prefetch SSD-resident KV into store DRAM while queued
- [Fix] benchmark: Isolate shared-prefix caches by tokenizer
- [Feat] mem_cache: Direct-linker support for plain MLA/MHA KV pools
- Docs
- Python not yet supported