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
- KV Cache Shard with Sequence Split
- [fix] Prefill delayer: make queue-timeout release deterministic across ranks
- [AMD] [GLM5] Fuse DSA indexer query Hadamard + FP8 quant into one Triton kernel (gfx950)
- fix(frontend): offload blocking request preprocessing
- fix(pd): align input limits across heterogeneous prefill/decode workers
- [HiCache]handle TP-replicated hybrid cache backups per pool
- [weight daemon] support draft model
- [dLLM] Schedule dLLM prefill and decode rows into one mixed round
- [AMD] [GLM5] Add opt-in PTPC FP8 projections on gfx950
- [AMD][DCP] Skip unused QuickAllReduce allocation for DCP groups
- Docs
- Python not yet supported