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
- [Test] Cover NPU MoE disk weight reload (#26794)
- [bugfix] Classify client cancel/disconnect aborts as HTTP 499 (not a successful finish)
- feat(kv-events): Add component_types field to BlockStored for per-component placement tracking
- DCP: native ncclAllToAll a2a backend with NCCL symmetric memory
- [HCU] Add Qwen3.5 and GLM-5 support
- [RFC] Asynchronous completion handling for the HiCache NIXL storage backend
- Fix DSA indexer aiter (HIP) padding mismatch under DP-attention
- [elastic-ep] Runtime scale-down: gracefully retire EP ranks via Mooncake deactivate_ranks
- [Bug] DeepSeek-V4-Flash-0731: reasoning_effort mapped one level off — `high` is a no-op and vendor `max` is unreachable
- [Feature][DCP] symm_a2a backend: peer-direct A2A for MLA decode on single-node NVLink/NVSwitch
- Docs
- Python not yet supported