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
- Enable Fused Shared Expert for FlashInfer TrtLLM FP8 Block-Scale MoE Backend
- refactor(runner): allocate attention static metadata buffers at eager init
- Rename and refactor `get_available_gpu_memory` function
- Adding missing test dependencies to all pyproject.toml
- [Feature] Support MTP/speculative decoding with hiSparse extra page draft zone
- Feat: add compact linear spec cache replay to reduce intermediate cache memory.
- [NPU][feature adapt] adp remote load weight without pta support
- [Bug] sglang v0.5.10 2 * H100 deploy glm5 report health check failed. server could not get a response from detokenizer for last 20 seconds
- [Perf][DSV4] add ag_gemm and moe_rs overlap kernels for dsv4 prefill
- [AMD] Add dense-FP8 for MXFP4 checkpoints with fused silu, mul, activation quant
- Docs
- Python not yet supported