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
- QSA prefill predicates: correctness claim withdrawn, pending maintainer review
- Fix shared-memory race in MoE alignment kernel
- fix(qsa): prevent out-of-bounds reads from padded extend plans
- [DeepSeek-V4] Fix duplicate shared-expert execution for built-in TP MoE
- [Bug] GLM-5.3-Flash (DSA): HiCache host-tier load-back corrupts generation even without speculative decoding — dropped tool calls, degenerate repetition loops (8×H100, TP8)
- [Feature] Per-request opt-out from prefix cache insertion (skip_cache_insert)
- [AMD][DSV4] Rename unified_kv to the ring KV layout and select it via --dsv4-kv-layout
- refactor: rename completion api token_ids to response_token_ids (supplement to #35225)
- fix: bound the DSA kpool ragged MQA logits allocation
- [Bug] Kimi-K3 strict tool-call grammar: additionalProperties dilutes a named property's type constraint
- Docs
- Python not yet supported