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] Report which limit bound `max_running_requests`
- fix: zero-init fp32 UE8M0 activation scales in the masked MoE down-GEMM
- fix: zero-init fp32 UE8M0 activation scales in the gemm1_alpha masked path
- [Fix] Take the attention backend name from the backend instead of `server_args`
- [misc] Expand the ruff pre-commit hook to the Pyflakes and pylint-error rule sets
- [Cleanup] Remove unused NUM_SMS parameter from _compute_pid
- refactor(dsv4): use explicit speculative forward state
- [DSpark PD 2/3] Integrate hidden-state bootstrap into PD scheduling
- [DSpark PD 3/3] Implement streaming hidden-state transfer for Mooncake
- [sglang-miles] Extract reasoning-request normalization into standalone helpers
- Docs
- Python not yet supported