get_rows & dequantize function implementation for repacked weights of type q4_K (q4_Kx8)

[swetha097]

• This implements the GGML_OP_GET_ROWS operation specifically for repacked (block interleaved) 4-bit quantized format (q4_Kx8)

• The following gains were observed by the changes made in the PR - The changes allow for increased usage of the GEMM function (ggml_gemm_q4_K_8x8_q8_K) for q4_K type

master branch commit - 17bece1885047dcf338c557a49f393677e265a91

development (get_rows) branch commit - 70cf05ae71fbabb1f943e13e4d27f41f890197f7

The PR was tested in AMD Raphael 7600X which supports the following flags :

system_info: n_threads = 4 / 12 | WHISPER : COREML = 0 | OPENVINO = 0 | CPU : SSE3 = 1 | SSSE3 = 1 | AVX = 1 | AVX2 = 1 | F16C = 1 | FMA = 1 | BMI2 = 1 | AVX512 = 1 | AVX512_VBMI = 1 | AVX512_VNNI = 1 | AVX512_BF16 = 1 | LLAMAFILE = 1 | REPACK = 1 |

Model for performance tests Downloaded from : https://huggingface.co/ggerganov/whisper.cpp/blob/main/ggml-base.en.bin and quantized to q4_0