wiki #quantization #quantization 4 pages tagged with "quantization" models mxfp4 quantization and gpu compute requirements — understanding gpu compute capability requirements for running mxfp4 quantized models like gpt-oss programming pytorch 2.8 release — pytorch 2.8 release notes with focus on training and inference performance quantization — 18+ quantization methods as first-class citizens in transformers v5.0 UE8M0 data format — 8-bit unsigned floating-point format for ai microscaling applications back to wiki