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] observability: Assign correct dp_rank under attention-dp for KV metrics and Prometheus
- [Perf] disaggregation: Batch prefill KV-send page-id readback across a batch
- [Fix] diffusion/bcg: Warm up LTX-2 two-stage at the output resolution
- [Perf] [AMD] attention: Attend AITER varlen's live prefix as one segment
- [Feat] dsv41: Share external HOST_NUMA Engram tables across P/D
- [CI] ci: Verify main after four-op squash (do not merge)
- [Fix] sglang-miles: Clear the multimodal embedding cache on flush_cache and weight updates
- [Performance] Reproducible cache hit-rate dip during L2/L3 capacity pressure with HiCache + Mooncake
- [Fix] disaggregation: Settle the in-flight decode result before a PD decode retraction
- [Fix] disaggregation: Back up separate draft KV pools in PD CPU retraction
- Docs
- Python not yet supported