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

ggml : fix YARN + add tests + add asserts (#7617)

Browse source 
* tests : add rope tests

ggml-ci

* ggml : fixes (hopefully)

ggml-ci

* tests : add non-cont tests

ggml-ci

* cuda : add asserts for rope/norm + fix DS2

ggml-ci

* ggml : assert contiguousness

* tests : reduce RoPE tests

ggml-ci
This commit is contained in:
Georgi Gerganov 2024-05-29 20:17:31 +03:00 • committed by GitHub
parent cce3dcffc5
commit fb76ec31a9
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
12 changed files with 167 additions and 104 deletions
Download patch file Download diff file Expand all files Collapse all files

77
tests/test-backend-ops.cpp
View file

@ -1138,26 +1138,37 @@ struct test_soft_max : public test_case {
// GGML_OP_ROPE
struct test_rope : public test_case {
const ggml_type type;
const std::array<int64_t, 4> ne;
const std::array<int64_t, 4> ne_a;
int n_dims;
int mode;
int n_ctx;
float fs; // freq_scale
float ef; // ext_factor
float af; // attn_factor
bool ff;
int v; // view (1 : non-contiguous a)
std::string vars() override {
return VARS_TO_STR6(type, ne, n_dims, mode, n_ctx, ff);
return VARS_TO_STR10(type, ne_a, n_dims, mode, n_ctx, fs, ef, af, ff, v);
}
test_rope(ggml_type type = GGML_TYPE_F32,
std::array<int64_t, 4> ne = {10, 10, 10, 1},
int n_dims = 10, int mode = 0, int n_ctx = 512, bool ff = false)
: type(type), ne(ne), n_dims(n_dims), mode(mode), n_ctx(n_ctx), ff(ff) {}
std::array<int64_t, 4> ne_a = {10, 10, 10, 1},
int n_dims = 10, int mode = 0, int n_ctx = 512, float fs = 1.0f, float ef = 0.0f, float af = 0.0f, bool ff = false, int v = 0)
: type(type), ne_a(ne_a), n_dims(n_dims), mode(mode), n_ctx(n_ctx), fs(fs), ef(ef), af(af), ff(ff), v(v) {}
ggml_tensor * build_graph(ggml_context * ctx) override {
ggml_tensor * a = ggml_new_tensor(ctx, type, 4, ne.data());
ggml_tensor * pos = ggml_new_tensor_1d(ctx, GGML_TYPE_I32, ne[2]);
ggml_tensor * a;
if (v & 1) {
auto ne = ne_a; ne[0] *= 2; ne[1] *= 4; ne[2] *= 3;
a = ggml_new_tensor(ctx, type, 4, ne.data());
a = ggml_view_4d(ctx, a, ne_a[0], ne_a[1], ne_a[2], ne_a[3], a->nb[1], a->nb[2], a->nb[3], 0);
} else {
a = ggml_new_tensor(ctx, type, 4, ne_a.data());
}
ggml_tensor * pos = ggml_new_tensor_1d(ctx, GGML_TYPE_I32, ne_a[2]);
ggml_tensor * freq = ff ? ggml_new_tensor_1d(ctx, GGML_TYPE_F32, n_dims/2) : nullptr;
ggml_tensor * out = ggml_rope_ext(ctx, a, pos, freq, n_dims, mode, n_ctx, 0, 10000.0f, 1.0f, 0.0f, 1.0f, 0.0f, 0.0f);
ggml_tensor * out = ggml_rope_ext(ctx, a, pos, freq, n_dims, mode, n_ctx, 0, 10000.0f, fs, ef, af, 1.0f, 1.0f);
return out;
}
@ -1165,11 +1176,11 @@ struct test_rope : public test_case {
for (ggml_tensor * t = ggml_get_first_tensor(ctx); t != NULL; t = ggml_get_next_tensor(ctx, t)) {
if (t->type == GGML_TYPE_I32) {
// pos
std::vector<int> data(ne[2]);
for (int i = 0; i < ne[2]; i++) {
std::vector<int> data(ne_a[2]);
for (int i = 0; i < ne_a[2]; i++) {
data[i] = rand() % n_ctx;
}
ggml_backend_tensor_set(t, data.data(), 0, ne[2] * sizeof(int));
ggml_backend_tensor_set(t, data.data(), 0, ne_a[2] * sizeof(int));
} else {
if (t->ne[0] == n_dims/2) {
// frequency factors in the range [0.9f, 1.1f]
@ -2213,20 +2224,38 @@ static bool test_backend(ggml_backend_t backend, test_mode mode, const char * op
test_cases.emplace_back(new test_soft_max(GGML_TYPE_F32, {32, 2, 32, 1}, true, 0.1f, 0.0f));
test_cases.emplace_back(new test_soft_max(GGML_TYPE_F32, {32, 2, 32, 1}, true, 0.1f, 8.0f));
for (ggml_type type : {GGML_TYPE_F32, GGML_TYPE_F16}) {
// TODO: ff not supported yet for !neox
test_cases.emplace_back(new test_rope(type, {128, 32, 10, 1}, 128, 0, 512, false)); // llama 7B
test_cases.emplace_back(new test_rope(type, {128, 40, 10, 1}, 128, 0, 512, false)); // llama 13B
test_cases.emplace_back(new test_rope(type, {128, 52, 10, 1}, 128, 0, 512, false)); // llama 30B
test_cases.emplace_back(new test_rope(type, {128, 64, 10, 1}, 128, 0, 512, false)); // llama 65B
{
bool all = true;
for (bool ff : {false, true}) { // freq_factors
test_cases.emplace_back(new test_rope(type, { 64, 1, 10, 1}, 64, 2, 512, ff)); // neox (falcon 7B)
test_cases.emplace_back(new test_rope(type, { 64, 71, 10, 1}, 64, 2, 512, ff)); // neox (falcon 7B)
test_cases.emplace_back(new test_rope(type, { 64, 8, 10, 1}, 64, 2, 512, ff)); // neox (falcon 40B)
test_cases.emplace_back(new test_rope(type, { 64, 128, 10, 1}, 64, 2, 512, ff)); // neox (falcon 40B)
test_cases.emplace_back(new test_rope(type, { 80, 32, 10, 1}, 20, 2, 512, ff)); // neox (stablelm)
test_cases.emplace_back(new test_rope(type, { 80, 32, 10, 1}, 32, 2, 512, ff)); // neox (phi-2)
for (float v : { 0, 1 }) {
for (float fs : { 1.0f, 1.4245f }) {
for (float ef : { 0.0f, 0.7465f }) {
for (float af : { 1.0f, 1.4245f }) {
for (ggml_type type : {GGML_TYPE_F32, GGML_TYPE_F16}) {
// TODO: ff not supported yet for !neox
test_cases.emplace_back(new test_rope(type, {128, 32, 10, 1}, 128, 0, 512, fs, ef, af, false, v)); // llama 7B
if (all) {
test_cases.emplace_back(new test_rope(type, {128, 40, 10, 1}, 128, 0, 512, fs, ef, af, false, v)); // llama 13B
test_cases.emplace_back(new test_rope(type, {128, 52, 10, 1}, 128, 0, 512, fs, ef, af, false, v)); // llama 30B
test_cases.emplace_back(new test_rope(type, {128, 64, 10, 1}, 128, 0, 512, fs, ef, af, false, v)); // llama 65B
}
for (bool ff : {false, true}) { // freq_factors
if (all) {
test_cases.emplace_back(new test_rope(type, { 64, 1, 10, 1}, 64, 2, 512, fs, ef, af, ff, v)); // neox (falcon 7B)
test_cases.emplace_back(new test_rope(type, { 64, 71, 10, 1}, 64, 2, 512, fs, ef, af, ff, v)); // neox (falcon 7B)
test_cases.emplace_back(new test_rope(type, { 64, 8, 10, 1}, 64, 2, 512, fs, ef, af, ff, v)); // neox (falcon 40B)
test_cases.emplace_back(new test_rope(type, { 80, 32, 10, 1}, 20, 2, 512, fs, ef, af, ff, v)); // neox (stablelm)
test_cases.emplace_back(new test_rope(type, { 80, 32, 10, 1}, 32, 2, 512, fs, ef, af, ff, v)); // neox (phi-2)
}
test_cases.emplace_back(new test_rope(type, { 64, 128, 10, 1}, 64, 2, 512, fs, ef, af, ff, v)); // neox (falcon 40B)
}
}
all = false;
}
}
}
}
}