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
- fix(server_args): drop the dead schedule_policy priority choice and reject it early
- Cosmos3 fp8 bug fix and action generation improvement
- [Feature] Reuse model-owned MTP weight selection before Default and RunAI shard reads
- [Spec] Apply sampling penalties under DFLASH and DSPARK
- [Transformers] Skip checkpoint keys HF ignores on load in the fallback loader
- Fix benchmark handling of streamed OpenAI server errors
- [diffusion] test: fix mesh Chamfer normalization and isolate sampling RNGs
- fix(nccl): disable graph buffer registration whenever a captured graph can hold a collective
- Fix Mooncake trace replay and warmup across benchmark backends
- Record client timing boundaries in serving benchmark details
- Docs
- Python not yet supported