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
- [HiCache] Reserve HiCache PP counts per in-flight ring round
- feat(hicache): restore exact prefixes before continuation arrival
- [diffusion] fix: give the scheduler hop its own host
- fix: handle JSON schema conversion correctly
- [AMD] Run the DCP verify prefix on MLA ASM as q_len=1 rows
- [Fix] SM120 sparse MLA: zero-initialise the 64-token page-split scratch so masked candidates never gather NaN from slot 0
- [Fix] mem_cache: keep a non-linear NextN layer out of the req-pool mamba layer list
- [Feature] function_call: opt-in strict DSML parsing for the DeepSeek V3.2 / V4 detectors
- [Feature] hicache: --hicache-mamba-size-gb for the hybrid host tier, plus per-pool host occupancy and eviction metrics
- [Fix] Redact credentials in server_args logging, /server_info and launch_command
- Docs
- Python not yet supported