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
- [Feature] Optimize the configuration and server startup of sgl-model-gateway
- [NPU] multi bs cp + L2 cache opt
- Zombie requests after client disconnect: abort_request fails to set to_finish during batch-transition window
- [Bug] DCP on GLM-5.3-Flash (norope MLA): virtual locs used raw against per-rank KV buffers — index-K OOB crash + state-dependent quality corruption past max_total_num_tokens
- [Bug] /unload_lora_adapter permanently deadlocks the scheduler after parallel-sampling traffic (n > 1)
- [Prefix Cache / Hybrid] Branch reuse silently collapses under LRU pressure when (kv_pool_tokens / chunked_prefill_size) > max_mamba_cache_size
- [Fix] Balance NVTX ranges when forward raises
- [Bug] Qwen3.8-Flash-Next + NEXTN full decode graph: repeated dual-rank invalid-probability asserts on GB10
- fix(arg_groups): reject NGRAM with --enable-linear-replayssm-spec
- [Feature] compute-mamba-ratio skill: plain-spec D is off the slot budget; admission clamp needs a +1 slot margin
- Docs
- Python not yet supported