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 supported3 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Feature]: Integrate `flash-infer` FP8 KV Cache Chunked-Prefill (Append Attention)
- [Usage]: Got nccl error when deploy vllm in k8s with multiple GPUs
- [Bug]: Dockerfile build error
- [Bug]: Pipeline parallelism is only supported through AsyncLLMEngine as performance will be severely degraded otherwise.
- [Bug]: Prefix cache with prompts dedupe
- [Misc]: How to use intel-gpu in openvino
- [Core] Move detokenization to front-end process
- [Usage]: KV Cache Warning for `gemma2`
- [Bug]: Bug in quantization/awq /gemm_kernels.cu gemm_forward_4bit_cuda_m16nXk32 More result have been write
- [Misc]: Cross-attention QKV computation is inefficient
- Docs
- Python not yet supported