Model quantization
Quantization represents model values or computations with lower numerical precision. It can reduce memory and increase throughput, but accuracy and hardware behavior depend on the chosen quantization method.
Overview. Quantization represents model values or computations with lower numerical precision.
Context. It can reduce memory and increase throughput, but accuracy and hardware behavior depend on the chosen quantization method.
Claims and evidence
Claim ledger, 2Quantization represents model values or computations with lower numerical precision.
It can reduce memory and increase throughput, but accuracy and hardware behavior depend on the chosen quantization method.