【深度学习模型部署框架】支持tf/torch/trt/trtllm/vllm以及更多nn框架,支持dynamic batching、streaming模式,支持python/c++双语言,可限制,可拓展,高性能。帮助用户快速地将模型部署到线上,并通过http/rpc接口方式提供服务。
-
Updated
Jan 10, 2025 - C++
【深度学习模型部署框架】支持tf/torch/trt/trtllm/vllm以及更多nn框架,支持dynamic batching、streaming模式,支持python/c++双语言,可限制,可拓展,高性能。帮助用户快速地将模型部署到线上,并通过http/rpc接口方式提供服务。
Dynamic batching library for Deep Learning inference. Tutorials for LLM, GPT scenarios.
InsNet Runs Instance-dependent Neural Networks with Padding-free Dynamic Batching.
Add a description, image, and links to the dynamic-batching topic page so that developers can more easily learn about it.
To associate your repository with the dynamic-batching topic, visit your repo's landing page and select "manage topics."