Skip to content

k-quants : fix quantization ranges #3646

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Oct 17, 2023
Merged

k-quants : fix quantization ranges #3646

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
30 changes: 11 additions & 19 deletions k_quants.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -462,12 +462,9 @@ void quantize_row_q2_K(const float * restrict x, void * restrict vy, int k) {
}

size_t ggml_quantize_q2_K(const float * restrict src, void * restrict dst, int n, int k, int64_t * restrict hist) {
const int nb = k / QK_K;

// TODO - collect histograms - although, at a second thought, I don't really care about them
(void)hist;
(void)hist; // TODO: collect histograms

for (int j = 0; j < nb; j += k) {
for (int j = 0; j < n; j += k) {
block_q2_K * restrict y = (block_q2_K *)dst + j/QK_K;
quantize_row_q2_K_reference(src + j, y, k);
}
Expand Down Expand Up @@ -678,12 +675,9 @@ void quantize_row_q3_K(const float * restrict x, void * restrict vy, int k) {
}

size_t ggml_quantize_q3_K(const float * restrict src, void * restrict dst, int n, int k, int64_t * restrict hist) {
const int nb = k / QK_K;

// TODO - collect histograms - although, at a second thought, I don't really care about them
(void)hist;
(void)hist; // TODO: collect histograms

for (int j = 0; j < nb; j += k) {
for (int j = 0; j < n; j += k) {
block_q3_K * restrict y = (block_q3_K *)dst + j/QK_K;
quantize_row_q3_K_reference(src + j, y, k);
}
Expand Down Expand Up @@ -846,9 +840,9 @@ void quantize_row_q4_K(const float * restrict x, void * restrict vy, int k) {

size_t ggml_quantize_q4_K(const float * restrict src, void * restrict dst, int n, int k, int64_t * restrict hist) {
assert(k % QK_K == 0);
const int nb = k / QK_K;
(void)hist; // TODO: collect histograms
for (int j = 0; j < nb; j += k) {

for (int j = 0; j < n; j += k) {
block_q4_K * restrict y = (block_q4_K *)dst + j/QK_K;
quantize_row_q4_K_reference(src + j, y, k);
}
Expand Down Expand Up @@ -1052,9 +1046,9 @@ void quantize_row_q5_K(const float * restrict x, void * restrict vy, int k) {

size_t ggml_quantize_q5_K(const float * restrict src, void * restrict dst, int n, int k, int64_t * restrict hist) {
assert(k % QK_K == 0);
const int nb = k / QK_K;
(void)hist;
for (int j = 0; j < nb; j += k) {
(void)hist; // TODO: collect histograms

for (int j = 0; j < n; j += k) {
block_q5_K * restrict y = (block_q5_K *)dst + j/QK_K;
quantize_row_q5_K_reference(src + j, y, k);
}
Expand Down Expand Up @@ -1200,11 +1194,9 @@ void quantize_row_q6_K(const float * restrict x, void * restrict vy, int k) {

size_t ggml_quantize_q6_K(const float * src, void * dst, int n, int k, int64_t * hist) {
assert(k % QK_K == 0);
const int nb = k / QK_K;

(void)hist; // TODO
(void)hist; // TODO: collect histograms

for (int j = 0; j < nb; j += k) {
for (int j = 0; j < n; j += k) {
block_q6_K * restrict y = (block_q6_K *)dst + j/QK_K;
quantize_row_q6_K_reference(src + j, y, k);
}
Expand Down