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
- [Docs] Lint: require --prerelease=allow on cookbook uv installs of sglang
- Fix FA3 page_table OOB near context wall under speculative decoding
- [Feature] Batch-wise Adaptive Pruning
- [NPU] Keep DeepSeek router GEMM output in fp32
- Fix MTP draft embed/lm_head dedup running after KV pool sizing
- fix(openai): guard before-validators against non-dict request bodies
- Fix output_dtype typo in block-wise quantization docstrings
- Add engine streaming response handler
- [Performance] Honor explicit workload caps when sizing hybrid cache
- [Bug] Qwen3.8-27B AWQ has no usable fast path on single Ada SM89 32GB: CUDA graph hangs and native MTP cannot allocate requests
- Docs
- Python not yet supported