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
- [Bug] EAGLE DSA draft backend misses KVIndexTranslator in FP8 MHA prefix reads
- fix(dsa): bind KV index translator to EAGLE draft backends
- feat(kv-events): advertise per-rank publisher endpoints
- [AMD][Fix] Incorrect vision token counting
- [Frontend] Add weighted multimodal preprocessing admission control
- feat: add fused CuTe DSL BF16 GEMM SiTU kernel
- [Test] Accounting-contract tests for classic RadixCache (+ sanity_check)
- killing straggler daemons leaves stale files. Unlink stale files.
- adaptive spec cuda graph buffer reuse
- [PoC] Split hybrid SWA allocator into `full`/`swa` sides and rename `*TokenToKVPoolAllocator` to `*KVAllocator`
- Docs
- Python not yet supported