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] Keep GPU JPEG decode from overwriting memory still in use
- [Refactor] trtllm_mha: inherit from AttentionBackend instead of FlashInferAttnBackend
- [WIP] fix aiter regression (aiter scout 166)
- [Bug]
- test: cover shared CPU offloader state
- [Bug] trtllm_mha: a NaN left in a reused KV page turns later requests into NaN
- [Fix] trtllm_mha: zero stale V rows past seq_len on the last KV page
- [DSV4.1][PD] Support the compatibility of decoder-swa-replay and BCG
- [ASR] Support Whisper speech translation via task selection
- [Fix] Skip HF Hub API calls for cached repos and honor --revision
- Docs
- Python not yet supported