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
- [Bug][Diffusion] --vae-tiling silently ignored for Sana: AutoencoderDC wrapper lacks enable_tiling, causing fatal OOM on 8GB GPUs
- Fix deterministic-mode shared-memory OutOfResources on sm_89: arch-aware persistent matmul configs
- [diffusion] post_training: honor lora_merge_mode in the LoRA IPC weight update
- [Spec] Sync MTP draft model weights on distributed (NCCL) online weight updates
- Fix dsv4 dspark swa pool accounting
- fix(benchmark): request token IDs when counting OpenAI prompts
- Rename NPU test files to reflect actual parallelism and rename MMMU test classes
- [model-gateway] Add rust analyzer component to toolchain
- feat(rust-server): support `save_remote_model` and `save_sharded_model`
- [AMD][DCP 3/N] add aiter asm for kimi k3 target verify
- Docs
- Python not yet supported