Search Results for "bit"

...The execution is significantly faster and requires less resources than general-purpose deep learning frameworks on supported models and tasks thanks to many advanced optimizations: layer fusion, padding removal, batch reordering, in-place operations, caching mechanism, etc. The model serialization and computation support weights with reduced precision: 16-bit floating points (FP16), 16-bit integers (INT16), and 8-bit integers (INT8). The project supports x86-64 and AArch64/ARM64 processors and integrates multiple backends that are optimized for these platforms: Intel MKL, oneDNN, OpenBLAS, Ruy, and Apple Accelerate.

neural-speed is an innovative library developed by Intel to enhance the efficiency of Large Language Model (LLM) inference through low-bit quantization techniques. By reducing the precision of model weights and activations, neural-speed aims to accelerate inference while maintaining model accuracy, making it suitable for deployment in resource-constrained environments.