Basic row-level quantization without importance matrix. These are reference implementations.
quantize_row_q4_0_ref(src_data, n_elements)quantize_row_q4_1_ref(src_data, n_elements)
quantize_row_q5_0_ref(src_data, n_elements)
quantize_row_q5_1_ref(src_data, n_elements)
quantize_row_q8_0_ref(src_data, n_elements)
quantize_row_q8_1_ref(src_data, n_elements)
Raw vector of quantized data
Numeric vector of float values to quantize
Number of elements to quantize
Other quantization:
dequantize_row_iq2_xxs(),
dequantize_row_mxfp4(),
dequantize_row_q2_K(),
dequantize_row_q4_0(),
dequantize_row_tq1_0(),
ggml_quant_block_info(),
iq2xs_free_impl(),
iq2xs_init_impl(),
iq3xs_free_impl(),
iq3xs_init_impl(),
quantize_iq2_xxs(),
quantize_mxfp4(),
quantize_q2_K(),
quantize_q4_0(),
quantize_row_iq3_xxs_ref(),
quantize_row_mxfp4_ref(),
quantize_row_q2_K_ref(),
quantize_row_tq1_0_ref(),
quantize_tq1_0()