vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Add ability to use importance matrix for all k-quants (#4930)

Browse source 
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
This commit is contained in:
Kawrakow 2024-01-14 16:21:12 +02:00 • committed by GitHub
parent bb0c139247
commit 467a882fd2
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
4 changed files with 462 additions and 16 deletions
Download patch file Download diff file Expand all files Collapse all files

28
ggml.c
View file

@ -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:
{