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 HF3FS metadata reservation at capacity
- [Bugfix] Retain global embedding cache hits through output assembly
- [Bugfix] Preserve multimodal cache entries when an item cannot fit
- [Feature] Share Ruff lint configuration with editors
- [Lint] Share Ruff configuration between editors and pre-commit
- [Rust] Reject full tokenizer queues without blocking intake
- [Rust] Skip queued tokenization for disconnected clients
- [Bug] `/hicache/storage-backend/clear` returns "Hierarchical cache storage backend cleared." with a 400 when it did not clear anything
- feat(model_loader): revive weight loader v2 dense tranche 1 (PR2 of #31051)
- [Bug] HiCacheFile scans the whole store directory on every existence check, so the scheduler stalls as the store grows
- Docs
- Python not yet supported