Skip to content

sync : ggml #14473

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 4 commits into from
Jul 1, 2025
Merged

sync : ggml #14473

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
a515220
ggml-quants : rename best_mad to best_error (ggml/1283)
danbev Jun 24, 2025
81ea009
ggml-cpu : "align corners" for bilinear upscale/downscale (ggml/1285)
Acly Jul 1, 2025
0a0c3c4
sync : ggml
ggerganov Jul 1, 2025
3db9e83
ggml : remove trailing whitespace (#0)
ggerganov Jul 1, 2025
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
22 changes: 20 additions & 2 deletions ggml/include/ggml.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1867,6 +1867,12 @@ extern "C" {
enum ggml_scale_mode {
GGML_SCALE_MODE_NEAREST = 0,
GGML_SCALE_MODE_BILINEAR = 1,

GGML_SCALE_MODE_COUNT
};

enum ggml_scale_flag {
GGML_SCALE_FLAG_ALIGN_CORNERS = (1 << 8)
};

// interpolate
Expand All @@ -1879,14 +1885,26 @@ extern "C" {

// interpolate
// interpolate scale to specified dimensions
GGML_API struct ggml_tensor * ggml_upscale_ext(
GGML_DEPRECATED(GGML_API struct ggml_tensor * ggml_upscale_ext(
struct ggml_context * ctx,
struct ggml_tensor * a,
int ne0,
int ne1,
int ne2,
int ne3,
enum ggml_scale_mode mode);
enum ggml_scale_mode mode),
"use ggml_interpolate instead");

// Up- or downsamples the input to the specified size.
// 2D scale modes (eg. bilinear) are applied to the first two dimensions.
GGML_API struct ggml_tensor * ggml_interpolate(
struct ggml_context * ctx,
struct ggml_tensor * a,
int64_t ne0,
int64_t ne1,
int64_t ne2,
int64_t ne3,
uint32_t mode); // ggml_scale_mode [ | ggml_scale_flag...]

// pad each dimension with zeros: [x, ..., x] -> [x, ..., x, 0, ..., 0]
GGML_API struct ggml_tensor * ggml_pad(
Expand Down
19 changes: 12 additions & 7 deletions ggml/src/ggml-cpu/ops.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7276,12 +7276,13 @@ static void ggml_compute_forward_upscale_f32(

GGML_TENSOR_UNARY_OP_LOCALS

const float sf0 = (float)ne0/src0->ne[0];
const float sf1 = (float)ne1/src0->ne[1];
const float sf2 = (float)ne2/src0->ne[2];
const float sf3 = (float)ne3/src0->ne[3];
float sf0 = (float)ne0/src0->ne[0];
float sf1 = (float)ne1/src0->ne[1];
float sf2 = (float)ne2/src0->ne[2];
float sf3 = (float)ne3/src0->ne[3];

const ggml_scale_mode mode = (ggml_scale_mode) ggml_get_op_params_i32(dst, 0);
const int32_t mode_flags = ggml_get_op_params_i32(dst, 0);
const ggml_scale_mode mode = (ggml_scale_mode) (mode_flags & 0xFF);

if (mode == GGML_SCALE_MODE_NEAREST) {
for (int64_t i3 = 0; i3 < ne3; i3++) {
Expand All @@ -7302,8 +7303,12 @@ static void ggml_compute_forward_upscale_f32(
}
}
} else if (mode == GGML_SCALE_MODE_BILINEAR) {
// setting a pixel offset of 0 would replicate the behavior of pytorch interpolate with align_corners=True
const float pixel_offset = 0.5f;
float pixel_offset = 0.5f;
if (mode_flags & GGML_SCALE_FLAG_ALIGN_CORNERS) {
pixel_offset = 0.0f;
sf0 = (float)(ne0 - 1) / (src0->ne[0] - 1);
sf1 = (float)(ne1 - 1) / (src0->ne[1] - 1);
}

for (int64_t i3 = 0; i3 < ne3; i3++) {
const int64_t i03 = i3 / sf3;
Expand Down
12 changes: 6 additions & 6 deletions ggml/src/ggml-quants.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -568,14 +568,14 @@ static float make_qkx2_quants(int n, int nmax, const float * GGML_RESTRICT x, co
}
float iscale = nmax/(max - min);
float scale = 1/iscale;
float best_mad = 0;
float best_error = 0;
for (int i = 0; i < n; ++i) {
int l = nearest_int(iscale*(x[i] - min));
L[i] = MAX(0, MIN(nmax, l));
float diff = scale * L[i] + min - x[i];
diff = use_mad ? fabsf(diff) : diff * diff;
float w = weights[i];
best_mad += w * diff;
best_error += w * diff;
}
if (nstep < 1) {
*the_min = -min;
Expand All @@ -601,18 +601,18 @@ static float make_qkx2_quants(int n, int nmax, const float * GGML_RESTRICT x, co
this_min = 0;
this_scale = sum_xl / sum_l2;
}
float mad = 0;
float cur_error = 0;
for (int i = 0; i < n; ++i) {
float diff = this_scale * Laux[i] + this_min - x[i];
diff = use_mad ? fabsf(diff) : diff * diff;
float w = weights[i];
mad += w * diff;
cur_error += w * diff;
}
if (mad < best_mad) {
if (cur_error < best_error) {
for (int i = 0; i < n; ++i) {
L[i] = Laux[i];
}
best_mad = mad;
best_error = cur_error;
scale = this_scale;
min = this_min;
}
Expand Down
37 changes: 23 additions & 14 deletions ggml/src/ggml.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4447,24 +4447,21 @@ struct ggml_tensor * ggml_pool_2d_back(
return result;
}

// ggml_upscale
// ggml_upscale / ggml_interpolate

static struct ggml_tensor * ggml_upscale_impl(
static struct ggml_tensor * ggml_interpolate_impl(
struct ggml_context * ctx,
struct ggml_tensor * a,
int ne0,
int ne1,
int ne2,
int ne3,
enum ggml_scale_mode mode) {
GGML_ASSERT(a->ne[0] <= ne0);
GGML_ASSERT(a->ne[1] <= ne1);
GGML_ASSERT(a->ne[2] <= ne2);
GGML_ASSERT(a->ne[3] <= ne3);
int64_t ne0,
int64_t ne1,
int64_t ne2,
int64_t ne3,
uint32_t mode) {
GGML_ASSERT((mode & 0xFF) < GGML_SCALE_MODE_COUNT);

struct ggml_tensor * result = ggml_new_tensor_4d(ctx, a->type, ne0, ne1, ne2, ne3);

ggml_set_op_params_i32(result, 0, mode);
ggml_set_op_params_i32(result, 0, (int32_t)mode);

result->op = GGML_OP_UPSCALE;
result->src[0] = a;
Expand All @@ -4477,7 +4474,8 @@ struct ggml_tensor * ggml_upscale(
struct ggml_tensor * a,
int scale_factor,
enum ggml_scale_mode mode) {
return ggml_upscale_impl(ctx, a, a->ne[0] * scale_factor, a->ne[1] * scale_factor, a->ne[2], a->ne[3], mode);
GGML_ASSERT(scale_factor > 1);
return ggml_interpolate_impl(ctx, a, a->ne[0] * scale_factor, a->ne[1] * scale_factor, a->ne[2], a->ne[3], mode);
}

struct ggml_tensor * ggml_upscale_ext(
Expand All @@ -4488,7 +4486,18 @@ struct ggml_tensor * ggml_upscale_ext(
int ne2,
int ne3,
enum ggml_scale_mode mode) {
return ggml_upscale_impl(ctx, a, ne0, ne1, ne2, ne3, mode);
return ggml_interpolate_impl(ctx, a, ne0, ne1, ne2, ne3, mode);
}

struct ggml_tensor * ggml_interpolate(
struct ggml_context * ctx,
struct ggml_tensor * a,
int64_t ne0,
int64_t ne1,
int64_t ne2,
int64_t ne3,
uint32_t mode) {
return ggml_interpolate_impl(ctx, a, ne0, ne1, ne2, ne3, mode);
}

// ggml_pad
Expand Down
2 changes: 1 addition & 1 deletion scripts/sync-ggml.last
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1 +1 @@
9e4bee1c5afc2d677a5b32ecb90cbdb483e81fff
67ad436cb653ac1ef0986f9fb0c6191ec828d1ed
16 changes: 9 additions & 7 deletions tests/test-backend-ops.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3296,28 +3296,28 @@ struct test_upscale : public test_case {
}
};

// GGML_OP_UPSCALE (ext)
struct test_upscale_ext : public test_case {
// GGML_OP_UPSCALE (via ggml_interpolate)
struct test_interpolate : public test_case {
const ggml_type type;
const std::array<int64_t, 4> ne;
const std::array<int64_t, 4> ne_tgt;
const ggml_scale_mode mode = GGML_SCALE_MODE_NEAREST;
const uint32_t mode = GGML_SCALE_MODE_NEAREST;

std::string vars() override {
return VARS_TO_STR4(type, ne, ne_tgt, mode);
}

test_upscale_ext(ggml_type type = GGML_TYPE_F32,
test_interpolate(ggml_type type = GGML_TYPE_F32,
std::array<int64_t, 4> ne = {2, 5, 7, 11},
std::array<int64_t, 4> ne_tgt = {5, 7, 11, 13},
ggml_scale_mode mode = GGML_SCALE_MODE_NEAREST)
uint32_t mode = GGML_SCALE_MODE_NEAREST)
: type(type), ne(ne), ne_tgt(ne_tgt), mode(mode) {}

ggml_tensor * build_graph(ggml_context * ctx) override {
ggml_tensor * a = ggml_new_tensor(ctx, type, 4, ne.data());
ggml_set_name(a, "a");

ggml_tensor * out = ggml_upscale_ext(ctx, a, ne_tgt[0], ne_tgt[1],ne_tgt[2], ne_tgt[3], mode);
ggml_tensor * out = ggml_interpolate(ctx, a, ne_tgt[0], ne_tgt[1],ne_tgt[2], ne_tgt[3], mode);
ggml_set_name(out, "out");

return out;
Expand Down Expand Up @@ -4799,8 +4799,10 @@ static std::vector<std::unique_ptr<test_case>> make_test_cases_eval() {
for (ggml_scale_mode mode : {GGML_SCALE_MODE_NEAREST, GGML_SCALE_MODE_BILINEAR}) {
test_cases.emplace_back(new test_upscale(GGML_TYPE_F32, {512, 512, 3, 2}, 2, mode));
test_cases.emplace_back(new test_upscale(GGML_TYPE_F32, {512, 512, 3, 2}, 2, mode, true));
test_cases.emplace_back(new test_upscale_ext(GGML_TYPE_F32, {2, 5, 7, 11}, {5, 7, 11, 13}, mode));
test_cases.emplace_back(new test_interpolate(GGML_TYPE_F32, {2, 5, 7, 11}, {5, 7, 11, 13}, mode));
test_cases.emplace_back(new test_interpolate(GGML_TYPE_F32, {5, 7, 11, 13}, {2, 5, 7, 11}, mode));
}
test_cases.emplace_back(new test_interpolate(GGML_TYPE_F32, {2, 5, 7, 11}, {5, 7, 11, 13}, GGML_SCALE_MODE_BILINEAR | GGML_SCALE_FLAG_ALIGN_CORNERS));

test_cases.emplace_back(new test_sum());
test_cases.emplace_back(new test_sum_rows());
Expand Down
Loading