SparseLLM

High-efficiency floating-point neural network inference operators for mobile, server, and Web

BladeDISC is an end-to-end DynamIc Shape Compiler project for machine learning workloads.

[MLSys 2021] IOS: Inter-Operator Scheduler for CNN Acceleration

A set of tool which would make your life easier with Tensorrt and Onnxruntime. This Repo is designed for YoloV3

Faster inference YOLOv8: Optimize and export YOLOv8 models for faster inference using OpenVINO and Numpy ?

[CVPR 2025] DivPrune: Diversity-based Visual Token Pruning for Large Multimodal Models

Your AI Catalyst: inference backend to maximize your model's inference performance

Batch Partitioning for Multi-PE Inference with TVM (2020)

Leveraging torch.compile to accelerate cross-encoder inference

A compilation of various ML and DL models and ways to optimize the their inferences.