vllm
https://github.com/vllm-project/vllm
Python
A high-throughput and memory-efficient inference and serving engine for LLMs
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 supported15 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Core] Make Whisper work with b200 + flashinfer
- [Feature]: GLM-4.6 spec decode with mtp
- [EPLB] Offline eplb support
- [Feature]: Batch Invariant Feature and Performance Optimization
- [FEAT] [Multi-modal] Reorganizing ViT Attention Backend and decouple from Text Attention Backend
- [Quantization] quantized kv cache loading for models like qwen
- [Feature]: Optimize collectives in TP MoE case using torch.compile pass
- Support compressed-tensors W4A8 MoE checkpoints in GptOssModel weight loader for CPU
- [Bugfix]: Streaming i/o of batch files. Resolves #30268
- [Performance]: DeepSeek-V3.2 AWQ Performance is lower then i expected
- Docs
- Python not yet supported