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
- [Perf] [Intel] gemma4: Fuse greedy verification logits finalization
- [Feature] kv-shard: Pass Q instead of KV for short prefills with long cached prefixes
- [Feat] PD: Support KV-only hybrid decode radix cache with MTP and DFlash2
- [Perf] [Intel] gemma4: Use exact softcap comparison ranks for greedy verification
- [Fix] mem_cache: Count unified-cache hits only on the finishing insert
- [Bug] Gemma4 input_embeds request crashes target prefill with input_ids/inputs_embeds exclusivity error
- [Bug] [AMD] --ep-dispatch-algorithm fake routes with the real correction bias on the aiter path
- [Fix] disaggregation: Preserve EAGLE/MTP draft KV during CPU retraction
- [Feat] [AMD] minimax_m3: Extend mono decode kernels to TP2 and TP8 on gfx950
- [Fix] speculative: Count proposals from completed adaptive rounds
- Docs
- Python not yet supported