GitHub

[ICLR'25] ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation

This repo contains the official code of our ICLR'25 paper: ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation. We introduce ViDiT-Q, a quantization ...
GitHub

llm-compressor/examples/quantization_w4a4_fp4 /llama3_example.py demo error: AttributeError: 'NoneType' object has no attribute 'shape'

Running the example script llm-compressor/examples/quantization_w4a4_fp4/llama3_example.py results in a runtime error. Full traceback is included below.
IEEE

Diversifying Sample Generation for Accurate Data-Free Quantization

Abstract: Quantization has emerged as one of the most prevalent approaches to compress and accelerate neural networks. Recently, data-free quantization has been widely studied as a practical and ...
IEEE

Low-Bit-Width Zero-Shot Quantization With Soft Feature-Infused Hints for IoT Systems

Abstract: Quantization has enabled the widespread implementation of deep learning algorithms on resource-constrained Internet of Things (IoT) devices, which compresses neural networks by reducing the ...
INSPIRE

Quantization of nonstandard Hamiltonian systems

The quantization of classical theories that admit more than one Hamiltonian description is considered. This is done from a geometrical viewpoint, both at the quantization level (geometric quantization ...