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

ggml : simplify ggml_quantize_chunk

Browse source 
ggml-ci
This commit is contained in:
Georgi Gerganov 2024-03-09 13:12:25 +02:00
parent 13c1cc6a9f
commit 2005b1f136
No known key found for this signature in database
GPG key ID: 449E073F9DC10735
2 changed files with 51 additions and 179 deletions
Download patch file Download diff file Expand all files Collapse all files

24
ggml-quants.h
View file

@ -261,6 +261,7 @@ void quantize_row_q4_K_reference(const float * GGML_RESTRICT x, block_q4_K * GGM
void quantize_row_q5_K_reference(const float * GGML_RESTRICT x, block_q5_K * GGML_RESTRICT y, int k); void quantize_row_q5_K_reference(const float * GGML_RESTRICT x, block_q5_K * GGML_RESTRICT y, int k);
void quantize_row_q6_K_reference(const float * GGML_RESTRICT x, block_q6_K * GGML_RESTRICT y, int k); void quantize_row_q6_K_reference(const float * GGML_RESTRICT x, block_q6_K * GGML_RESTRICT y, int k);
void quantize_row_q8_K_reference(const float * GGML_RESTRICT x, block_q8_K * GGML_RESTRICT y, int k); void quantize_row_q8_K_reference(const float * GGML_RESTRICT x, block_q8_K * GGML_RESTRICT y, int k);
void quantize_row_iq3_xxs_reference(const float * GGML_RESTRICT x, block_iq3_xxs * GGML_RESTRICT y, int k); void quantize_row_iq3_xxs_reference(const float * GGML_RESTRICT x, block_iq3_xxs * GGML_RESTRICT y, int k);
void quantize_row_iq4_nl_reference (const float * GGML_RESTRICT x, block_iq4_nl * GGML_RESTRICT y, int k); void quantize_row_iq4_nl_reference (const float * GGML_RESTRICT x, block_iq4_nl * GGML_RESTRICT y, int k);
void quantize_row_iq4_xs_reference (const float * GGML_RESTRICT x, block_iq4_xs * GGML_RESTRICT y, int k); void quantize_row_iq4_xs_reference (const float * GGML_RESTRICT x, block_iq4_xs * GGML_RESTRICT y, int k);
@ -280,6 +281,7 @@ void quantize_row_q4_K(const float * GGML_RESTRICT x, void * GGML_RESTRICT y, in
void quantize_row_q5_K(const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int k); void quantize_row_q5_K(const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int k);
void quantize_row_q6_K(const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int k); void quantize_row_q6_K(const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int k);
void quantize_row_q8_K(const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int k); void quantize_row_q8_K(const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int k);
void quantize_row_iq3_xxs(const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int k); void quantize_row_iq3_xxs(const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int k);
void quantize_row_iq4_nl (const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int k); void quantize_row_iq4_nl (const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int k);
void quantize_row_iq4_xs (const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int k); void quantize_row_iq4_xs (const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int k);
@ -300,6 +302,7 @@ void dequantize_row_q4_K(const block_q4_K * GGML_RESTRICT x, float * GGML_RESTRI
void dequantize_row_q5_K(const block_q5_K * GGML_RESTRICT x, float * GGML_RESTRICT y, int k); void dequantize_row_q5_K(const block_q5_K * GGML_RESTRICT x, float * GGML_RESTRICT y, int k);
void dequantize_row_q6_K(const block_q6_K * GGML_RESTRICT x, float * GGML_RESTRICT y, int k); void dequantize_row_q6_K(const block_q6_K * GGML_RESTRICT x, float * GGML_RESTRICT y, int k);
void dequantize_row_q8_K(const block_q8_K * GGML_RESTRICT x, float * GGML_RESTRICT y, int k); void dequantize_row_q8_K(const block_q8_K * GGML_RESTRICT x, float * GGML_RESTRICT y, int k);
void dequantize_row_iq2_xxs(const block_iq2_xxs * GGML_RESTRICT x, float * GGML_RESTRICT y, int k); void dequantize_row_iq2_xxs(const block_iq2_xxs * GGML_RESTRICT x, float * GGML_RESTRICT y, int k);
void dequantize_row_iq2_xs (const block_iq2_xs * GGML_RESTRICT x, float * GGML_RESTRICT y, int k); void dequantize_row_iq2_xs (const block_iq2_xs * GGML_RESTRICT x, float * GGML_RESTRICT y, int k);
void dequantize_row_iq2_s (const block_iq2_s * GGML_RESTRICT x, float * GGML_RESTRICT y, int k); void dequantize_row_iq2_s (const block_iq2_s * GGML_RESTRICT x, float * GGML_RESTRICT y, int k);
@ -341,16 +344,17 @@ size_t quantize_iq1_s (const float * src, void * dst, int nrows, int n_per_row,
size_t quantize_iq4_nl (const float * src, void * dst, int nrows, int n_per_row, const float * imatrix); size_t quantize_iq4_nl (const float * src, void * dst, int nrows, int n_per_row, const float * imatrix);
size_t quantize_iq4_xs (const float * src, void * dst, int nrows, int n_per_row, const float * imatrix); size_t quantize_iq4_xs (const float * src, void * dst, int nrows, int n_per_row, const float * imatrix);
size_t quantize_iq3_s (const float * src, void * dst, int nrows, int n_per_row, const float * imatrix); size_t quantize_iq3_s (const float * src, void * dst, int nrows, int n_per_row, const float * imatrix);
size_t quantize_q2_K (const float * src, void * dst, int nrows, int n_per_row, const float * imatrix);
size_t quantize_q3_K (const float * src, void * dst, int nrows, int n_per_row, const float * imatrix); size_t quantize_q2_K(const float * src, void * dst, int nrows, int n_per_row, const float * imatrix);
size_t quantize_q4_K (const float * src, void * dst, int nrows, int n_per_row, const float * imatrix); size_t quantize_q3_K(const float * src, void * dst, int nrows, int n_per_row, const float * imatrix);
size_t quantize_q5_K (const float * src, void * dst, int nrows, int n_per_row, const float * imatrix); size_t quantize_q4_K(const float * src, void * dst, int nrows, int n_per_row, const float * imatrix);
size_t quantize_q6_K (const float * src, void * dst, int nrows, int n_per_row, const float * imatrix); size_t quantize_q5_K(const float * src, void * dst, int nrows, int n_per_row, const float * imatrix);
size_t quantize_q4_0 (const float * src, void * dst, int nrows, int n_per_row, const float * imatrix); size_t quantize_q6_K(const float * src, void * dst, int nrows, int n_per_row, const float * imatrix);
size_t quantize_q4_1 (const float * src, void * dst, int nrows, int n_per_row, const float * imatrix); size_t quantize_q4_0(const float * src, void * dst, int nrows, int n_per_row, const float * imatrix);
size_t quantize_q5_0 (const float * src, void * dst, int nrows, int n_per_row, const float * imatrix); size_t quantize_q4_1(const float * src, void * dst, int nrows, int n_per_row, const float * imatrix);
size_t quantize_q5_1 (const float * src, void * dst, int nrows, int n_per_row, const float * imatrix); size_t quantize_q5_0(const float * src, void * dst, int nrows, int n_per_row, const float * imatrix);
size_t quantize_q8_0 (const float * src, void * dst, int nrows, int n_per_row, const float * imatrix); size_t quantize_q5_1(const float * src, void * dst, int nrows, int n_per_row, const float * imatrix);
size_t quantize_q8_0(const float * src, void * dst, int nrows, int n_per_row, const float * imatrix);
void iq2xs_init_impl(enum ggml_type type); void iq2xs_init_impl(enum ggml_type type);
void iq2xs_free_impl(enum ggml_type type); void iq2xs_free_impl(enum ggml_type type);

206
ggml.c
View file

@ -20175,178 +20175,44 @@ size_t ggml_quantize_chunk(
int n_per_row, int n_per_row,
int64_t * hist, int64_t * hist,
const float * imatrix) { const float * imatrix) {
const int n = nrows * n_per_row;
if (ggml_quantize_requires_imatrix(type)) {
GGML_ASSERT(imatrix != NULL);
}
GGML_ASSERT(start % type_traits[type].blck_size == 0);
GGML_ASSERT(start % n_per_row == 0);
ggml_quantize_init(type); // this is noop if already initialized ggml_quantize_init(type); // this is noop if already initialized
const size_t start_row = start / n_per_row;
const size_t row_size = ggml_row_size(type, n_per_row);
size_t result = 0; size_t result = 0;
int n = nrows * n_per_row;
switch (type) { switch (type) {
case GGML_TYPE_Q4_0: case GGML_TYPE_Q4_0: result = quantize_q4_0(src + start, (char *) dst + start_row * row_size, nrows, n_per_row, imatrix); break;
{ case GGML_TYPE_Q4_1: result = quantize_q4_1(src + start, (char *) dst + start_row * row_size, nrows, n_per_row, imatrix); break;
GGML_ASSERT(start % QK4_0 == 0); case GGML_TYPE_Q5_0: result = quantize_q5_0(src + start, (char *) dst + start_row * row_size, nrows, n_per_row, imatrix); break;
GGML_ASSERT(start % n_per_row == 0); case GGML_TYPE_Q5_1: result = quantize_q5_1(src + start, (char *) dst + start_row * row_size, nrows, n_per_row, imatrix); break;
size_t start_row = start / n_per_row; case GGML_TYPE_Q8_0: result = quantize_q8_0(src + start, (char *) dst + start_row * row_size, nrows, n_per_row, imatrix); break;
size_t row_size = ggml_row_size(type, n_per_row); case GGML_TYPE_Q2_K: result = quantize_q2_K(src + start, (char *) dst + start_row * row_size, nrows, n_per_row, imatrix); break;
result = quantize_q4_0(src + start, (char *)dst + start_row * row_size, nrows, n_per_row, imatrix); case GGML_TYPE_Q3_K: result = quantize_q3_K(src + start, (char *) dst + start_row * row_size, nrows, n_per_row, imatrix); break;
GGML_ASSERT(result == row_size * nrows); case GGML_TYPE_Q4_K: result = quantize_q4_K(src + start, (char *) dst + start_row * row_size, nrows, n_per_row, imatrix); break;
} break; case GGML_TYPE_Q5_K: result = quantize_q5_K(src + start, (char *) dst + start_row * row_size, nrows, n_per_row, imatrix); break;
case GGML_TYPE_Q4_1: case GGML_TYPE_Q6_K: result = quantize_q6_K(src + start, (char *) dst + start_row * row_size, nrows, n_per_row, imatrix); break;
{ case GGML_TYPE_IQ2_XXS: result = quantize_iq2_xxs(src + start, (char *) dst + start_row * row_size, nrows, n_per_row, imatrix); break;
GGML_ASSERT(start % QK4_1 == 0); case GGML_TYPE_IQ2_XS: result = quantize_iq2_xs (src + start, (char *) dst + start_row * row_size, nrows, n_per_row, imatrix); break;
GGML_ASSERT(start % n_per_row == 0); case GGML_TYPE_IQ3_XXS: result = quantize_iq3_xxs(src + start, (char *) dst + start_row * row_size, nrows, n_per_row, imatrix); break;
size_t start_row = start / n_per_row; case GGML_TYPE_IQ3_S: result = quantize_iq3_s (src + start, (char *) dst + start_row * row_size, nrows, n_per_row, imatrix); break;
size_t row_size = ggml_row_size(type, n_per_row); case GGML_TYPE_IQ2_S: result = quantize_iq2_s (src + start, (char *) dst + start_row * row_size, nrows, n_per_row, imatrix); break;
result = quantize_q4_1(src + start, (char *)dst + start_row * row_size, nrows, n_per_row, imatrix); case GGML_TYPE_IQ1_S: result = quantize_iq1_s (src + start, (char *) dst + start_row * row_size, nrows, n_per_row, imatrix); break;
GGML_ASSERT(result == row_size * nrows); case GGML_TYPE_IQ4_NL: result = quantize_iq4_nl (src + start, (char *) dst + start_row * row_size, nrows, n_per_row, imatrix); break;
} break;
case GGML_TYPE_Q5_0:
{
GGML_ASSERT(start % QK5_0 == 0);
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_0(src + start, (char *)dst + start_row * row_size, nrows, n_per_row, imatrix);
GGML_ASSERT(result == row_size * nrows);
} break;
case GGML_TYPE_Q5_1:
{
GGML_ASSERT(start % QK5_1 == 0);
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_1(src + start, (char *)dst + start_row * row_size, nrows, n_per_row, imatrix);
GGML_ASSERT(result == row_size * nrows);
} break;
case GGML_TYPE_Q8_0:
{
GGML_ASSERT(start % QK8_0 == 0);
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_q8_0(src + start, (char *)dst + start_row * row_size, nrows, n_per_row, imatrix);
GGML_ASSERT(result == row_size * nrows);
} break;
case GGML_TYPE_Q2_K:
{
GGML_ASSERT(start % QK_K == 0);
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_q2_K(src + start, (char *)dst + start_row * row_size, nrows, n_per_row, imatrix);
GGML_ASSERT(result == row_size * nrows);
} break;
case GGML_TYPE_Q3_K:
{
GGML_ASSERT(start % QK_K == 0);
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, imatrix);
GGML_ASSERT(result == row_size * nrows);
} break;
case GGML_TYPE_Q4_K:
{
GGML_ASSERT(start % QK_K == 0);
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, imatrix);
GGML_ASSERT(result == row_size * nrows);
} break;
case GGML_TYPE_Q5_K:
{
GGML_ASSERT(start % QK_K == 0);
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, imatrix);
GGML_ASSERT(result == row_size * nrows);
} break;
case GGML_TYPE_Q6_K:
{
GGML_ASSERT(start % QK_K == 0);
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, imatrix);
GGML_ASSERT(result == row_size * nrows);
} break;
case GGML_TYPE_IQ2_XXS:
{
GGML_ASSERT(start % QK_K == 0);
GGML_ASSERT(start % n_per_row == 0);
GGML_ASSERT(imatrix);
size_t start_row = start / n_per_row;
size_t row_size = ggml_row_size(type, n_per_row);
result = quantize_iq2_xxs(src + start, (char *)dst + start_row * row_size, nrows, n_per_row, imatrix);
GGML_ASSERT(result == row_size * nrows);
} break;
case GGML_TYPE_IQ2_XS:
{
GGML_ASSERT(start % QK_K == 0);
GGML_ASSERT(start % n_per_row == 0);
GGML_ASSERT(imatrix);
size_t start_row = start / n_per_row;
size_t row_size = ggml_row_size(type, n_per_row);
result = quantize_iq2_xs(src + start, (char *)dst + start_row * row_size, nrows, n_per_row, imatrix);
GGML_ASSERT(result == row_size * nrows);
} break;
case GGML_TYPE_IQ3_XXS:
{
GGML_ASSERT(start % QK_K == 0);
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_iq3_xxs(src + start, (char *)dst + start_row * row_size, nrows, n_per_row, imatrix);
GGML_ASSERT(result == row_size * nrows);
} break;
case GGML_TYPE_IQ3_S:
{
GGML_ASSERT(start % QK_K == 0);
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_iq3_s(src + start, (char *)dst + start_row * row_size, nrows, n_per_row, imatrix);
GGML_ASSERT(result == row_size * nrows);
} break;
case GGML_TYPE_IQ2_S:
{
GGML_ASSERT(start % QK_K == 0);
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_iq2_s(src + start, (char *)dst + start_row * row_size, nrows, n_per_row, imatrix);
GGML_ASSERT(result == row_size * nrows);
} break;
case GGML_TYPE_IQ1_S:
{
GGML_ASSERT(start % QK_K == 0);
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_iq1_s(src + start, (char *)dst + start_row * row_size, nrows, n_per_row, imatrix);
GGML_ASSERT(result == row_size * nrows);
} break;
case GGML_TYPE_IQ4_NL:
#if QK_K == 64 #if QK_K == 64
case GGML_TYPE_IQ4_XS: case GGML_TYPE_IQ4_XS: result = quantize_iq4_nl (src + start, (char *) dst + start_row * row_size, nrows, n_per_row, imatrix); break;
#endif #else
{ case GGML_TYPE_IQ4_XS: result = quantize_iq4_xs (src + start, (char *) dst + start_row * row_size, nrows, n_per_row, imatrix); break;
GGML_ASSERT(start % QK4_NL == 0);
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_iq4_nl(src + start, (char *)dst + start_row * row_size, nrows, n_per_row, imatrix);
GGML_ASSERT(result == row_size * nrows);
} break;
#if QK_K != 64
case GGML_TYPE_IQ4_XS:
{
GGML_ASSERT(start % QK_K == 0);
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_iq4_xs(src + start, (char *)dst + start_row * row_size, nrows, n_per_row, imatrix);
GGML_ASSERT(result == row_size * nrows);
} break;
#endif #endif
case GGML_TYPE_F16: case GGML_TYPE_F16:
{ {
@ -20364,7 +20230,9 @@ size_t ggml_quantize_chunk(
assert(false); assert(false);
} }
GGML_UNUSED(hist); // TODO: poppulate GGML_ASSERT(result == nrows * row_size);
GGML_UNUSED(hist); // TODO: populate
return result; return result;
} }