Mojo module
fp8_quantization
Functions
-
convert_e4m3fn_to_e4m3fnuz
: Convert E4M3FN weights to E4M3FNUZ format for AMD GPU compatibility. -
matmul_dynamic_scaled_fp8
: -
naive_blockwise_scaled_fp8_grouped_matmul
: -
naive_blockwise_scaled_fp8_grouped_matmul_kernel
: -
naive_blockwise_scaled_fp8_matmul
: -
naive_blockwise_scaled_fp8_matmul_kernel
: -
quantize_dynamic_scaled_fp8
: -
quantize_fp8_kernel
: -
quantize_static_scaled_fp8
:
Was this page helpful?
Thank you! We'll create more content like this.
Thank you for helping us improve!