dynamic-batching topic

List dynamic-batching repositories

InsNet

65
Stars
12
Forks
Watchers

InsNet Runs Instance-dependent Neural Networks with Padding-free Dynamic Batching.

batch-inference

65
Stars
0
Forks
Watchers

Dynamic batching library for Deep Learning inference. Tutorials for LLM, GPT scenarios.

grps

147
Stars
13
Forks
Watchers

【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...