From 467a882fd2e5b6172897b49aa45aa29bd3f27685 Mon Sep 17 00:00:00 2001 From: Kawrakow <48489457+ikawrakow@users.noreply.github.com> Date: Sun, 14 Jan 2024 16:21:12 +0200 Subject: Add ability to use importance matrix for all k-quants (#4930) Co-authored-by: Iwan Kawrakow --- ggml.c | 28 ++++++++++++++++++++-------- 1 file changed, 20 insertions(+), 8 deletions(-) (limited to 'ggml.c') diff --git a/ggml.c b/ggml.c index 52467475..ef5888ab 100644 --- a/ggml.c +++ b/ggml.c @@ -18713,26 +18713,38 @@ size_t ggml_quantize_chunk(enum ggml_type type, const float * src, void * dst, i case GGML_TYPE_Q3_K: { GGML_ASSERT(start % QK_K == 0); - block_q3_K * block = (block_q3_K*)dst + start / QK_K; - result = ggml_quantize_q3_K(src + start, block, n, n, hist); + GGML_ASSERT(start % n_per_row == 0); + size_t start_row = start / n_per_row; + size_t row_size = ggml_row_size(type, n_per_row); + result = quantize_q3_K(src + start, (char *)dst + start_row * row_size, nrows, n_per_row, hist, imatrix); + GGML_ASSERT(result == row_size * nrows); } break; case GGML_TYPE_Q4_K: { GGML_ASSERT(start % QK_K == 0); - block_q4_K * block = (block_q4_K*)dst + start / QK_K; - result = ggml_quantize_q4_K(src + start, block, n, n, hist); + GGML_ASSERT(start % n_per_row == 0); + size_t start_row = start / n_per_row; + size_t row_size = ggml_row_size(type, n_per_row); + result = quantize_q4_K(src + start, (char *)dst + start_row * row_size, nrows, n_per_row, hist, imatrix); + GGML_ASSERT(result == row_size * nrows); } break; case GGML_TYPE_Q5_K: { GGML_ASSERT(start % QK_K == 0); - block_q5_K * block = (block_q5_K*)dst + start / QK_K; - result = ggml_quantize_q5_K(src + start, block, n, n, hist); + GGML_ASSERT(start % n_per_row == 0); + size_t start_row = start / n_per_row; + size_t row_size = ggml_row_size(type, n_per_row); + result = quantize_q5_K(src + start, (char *)dst + start_row * row_size, nrows, n_per_row, hist, imatrix); + GGML_ASSERT(result == row_size * nrows); } break; case GGML_TYPE_Q6_K: { GGML_ASSERT(start % QK_K == 0); - block_q6_K * block = (block_q6_K*)dst + start / QK_K; - result = ggml_quantize_q6_K(src + start, block, n, n, hist); + GGML_ASSERT(start % n_per_row == 0); + size_t start_row = start / n_per_row; + size_t row_size = ggml_row_size(type, n_per_row); + result = quantize_q6_K(src + start, (char *)dst + start_row * row_size, nrows, n_per_row, hist, imatrix); + GGML_ASSERT(result == row_size * nrows); } break; case GGML_TYPE_IQ2_XXS: { -- cgit v1.2.3