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

RoPE: fix back, CUDA support for back + noncont. (#11240)

Browse source 
* RoPE: fix back, CUDA support for back + noncont.

* fix comments reg. non-cont. RoPE support [no-ci]
This commit is contained in:
Johannes Gäßler 2025-01-15 12:51:37 +01:00 • committed by GitHub
parent 0ccd7f3eb2
commit 432df2d5f9
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
9 changed files with 269 additions and 258 deletions
Download patch file Download diff file Expand all files Collapse all files

63
tests/test-backend-ops.cpp
View file

@ -2192,7 +2192,7 @@ struct test_soft_max : public test_case {
};
// GGML_OP_ROPE
// GGML_OP_ROPE + GGML_OP_ROPE_BACK
struct test_rope : public test_case {
const ggml_type type;
const std::array<int64_t, 4> ne_a;
@ -2204,29 +2204,36 @@ struct test_rope : public test_case {
float af; // attn_factor
bool ff;
int v; // view (1 : non-contiguous a)
bool forward;
std::string vars() override {
// forward can be inferred from the op, does not need to be printed
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_a = {10, 5, 3, 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) {}
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, bool forward = true)
: 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), forward(forward) {}
ggml_tensor * build_graph(ggml_context * ctx) override {
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());
ggml_set_param(ctx, a);
if (forward) {
ggml_set_param(ctx, a);
}
ggml_set_name(a, "a");
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);
ggml_set_name(a, "view_of_a");
} else {
a = ggml_new_tensor(ctx, type, 4, ne_a.data());
ggml_set_param(ctx, a);
if (forward) {
ggml_set_param(ctx, a);
}
ggml_set_name(a, "a");
}
@ -2252,14 +2259,26 @@ struct test_rope : public test_case {
if (is_vision) {
GGML_ASSERT(n_dims/4 > 0);
int rope_sections[4] = {n_dims/4, n_dims/4, 0, 0}; // Vision-RoPE only use first two dimension for image (x, y) coordinate
out = ggml_rope_multi(ctx, a, pos, freq, n_dims/2, rope_sections, mode, 0, 10000.0f, fs, ef, af, 1.0f, 1.0f);
if (forward) {
out = ggml_rope_multi (ctx, a, pos, freq, n_dims/2, rope_sections, mode, 0, 10000.0f, fs, ef, af, 1.0f, 1.0f);
} else {
out = ggml_rope_multi_back(ctx, a, pos, freq, n_dims/2, rope_sections, mode, 0, 10000.0f, fs, ef, af, 1.0f, 1.0f);
}
} else {
GGML_ASSERT(n_dims/3 > 0);
int rope_sections[4] = {n_dims/3, n_dims/3, n_dims/3, 0};
out = ggml_rope_multi(ctx, a, pos, freq, n_dims, rope_sections, mode, 0, 10000.0f, fs, ef, af, 1.0f, 1.0f);
if (forward) {
out = ggml_rope_multi (ctx, a, pos, freq, n_dims, rope_sections, mode, 0, 10000.0f, fs, ef, af, 1.0f, 1.0f);
} else {
out = ggml_rope_multi_back(ctx, a, pos, freq, n_dims, rope_sections, mode, 0, 10000.0f, fs, ef, af, 1.0f, 1.0f);
}
}
} else {
out = ggml_rope_ext(ctx, a, pos, freq, n_dims, mode, 0, 10000.0f, fs, ef, af, 1.0f, 1.0f);
if (forward) {
out = ggml_rope_ext (ctx, a, pos, freq, n_dims, mode, 0, 10000.0f, fs, ef, af, 1.0f, 1.0f);
} else {
out = ggml_rope_ext_back(ctx, a, pos, freq, n_dims, mode, 0, 10000.0f, fs, ef, af, 1.0f, 1.0f);
}
}
ggml_set_name(out, "out");
@ -3844,7 +3863,7 @@ static std::vector<std::unique_ptr<test_case>> make_test_cases_eval() {
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 (bool fw : {true, false}) { // fw == forward
bool all = true;
for (float v : { 0, 1 }) {
@ -3853,29 +3872,29 @@ static std::vector<std::unique_ptr<test_case>> make_test_cases_eval() {
for (float af : { 1.0f, 1.4245f }) {
for (ggml_type type : {GGML_TYPE_F32, GGML_TYPE_F16}) {
for (bool ff : {false, true}) { // freq_factors
test_cases.emplace_back(new test_rope(type, {128, 32, 2, 1}, 128, 0, 512, fs, ef, af, ff, v)); // llama 7B
test_cases.emplace_back(new test_rope(type, {128, 32, 2, 1}, 128, 0, 512, fs, ef, af, ff, v, fw)); // llama 7B
if (all) {
test_cases.emplace_back(new test_rope(type, {128, 40, 2, 1}, 128, 0, 512, fs, ef, af, ff, v)); // llama 13B
test_cases.emplace_back(new test_rope(type, {128, 52, 2, 1}, 128, 0, 512, fs, ef, af, ff, v)); // llama 30B
test_cases.emplace_back(new test_rope(type, {128, 64, 2, 1}, 128, 0, 512, fs, ef, af, ff, v)); // llama 65B
test_cases.emplace_back(new test_rope(type, {128, 40, 2, 1}, 128, 0, 512, fs, ef, af, ff, v, fw)); // llama 13B
test_cases.emplace_back(new test_rope(type, {128, 52, 2, 1}, 128, 0, 512, fs, ef, af, ff, v, fw)); // llama 30B
test_cases.emplace_back(new test_rope(type, {128, 64, 2, 1}, 128, 0, 512, fs, ef, af, ff, v, fw)); // llama 65B
}
if (all) {
test_cases.emplace_back(new test_rope(type, { 64, 1, 2, 1}, 64, 2, 512, fs, ef, af, ff, v)); // neox (falcon 7B)
test_cases.emplace_back(new test_rope(type, { 64, 71, 2, 1}, 64, 2, 512, fs, ef, af, ff, v)); // neox (falcon 7B)
test_cases.emplace_back(new test_rope(type, { 64, 8, 2, 1}, 64, 2, 512, fs, ef, af, ff, v)); // neox (falcon 40B)
test_cases.emplace_back(new test_rope(type, { 80, 32, 2, 1}, 20, 2, 512, fs, ef, af, ff, v)); // neox (stablelm)
test_cases.emplace_back(new test_rope(type, { 80, 32, 2, 1}, 32, 2, 512, fs, ef, af, ff, v)); // neox (phi-2)
test_cases.emplace_back(new test_rope(type, { 64, 1, 2, 1}, 64, 2, 512, fs, ef, af, ff, v, fw)); // neox (falcon 7B)
test_cases.emplace_back(new test_rope(type, { 64, 71, 2, 1}, 64, 2, 512, fs, ef, af, ff, v, fw)); // neox (falcon 7B)
test_cases.emplace_back(new test_rope(type, { 64, 8, 2, 1}, 64, 2, 512, fs, ef, af, ff, v, fw)); // neox (falcon 40B)
test_cases.emplace_back(new test_rope(type, { 80, 32, 2, 1}, 20, 2, 512, fs, ef, af, ff, v, fw)); // neox (stablelm)
test_cases.emplace_back(new test_rope(type, { 80, 32, 2, 1}, 32, 2, 512, fs, ef, af, ff, v, fw)); // neox (phi-2)
}
if (all) {
test_cases.emplace_back(new test_rope(type, {128, 12, 2, 1}, 128, GGML_ROPE_TYPE_MROPE, 512, fs, ef, af, ff, v)); // rope_multi,m-rope (qwen2vl 2B)
test_cases.emplace_back(new test_rope(type, {128, 28, 2, 1}, 128, GGML_ROPE_TYPE_MROPE, 512, fs, ef, af, ff, v)); // rope_multi,m-rope (qwen2vl 7B)
test_cases.emplace_back(new test_rope(type, { 80, 16, 2, 1}, 80, GGML_ROPE_TYPE_VISION, 512, fs, ef, af, ff, v)); // rope_multi,m-rope (qwen2vl ViT)
test_cases.emplace_back(new test_rope(type, {128, 12, 2, 1}, 128, GGML_ROPE_TYPE_MROPE, 512, fs, ef, af, ff, v, fw)); // rope_multi,m-rope (qwen2vl 2B)
test_cases.emplace_back(new test_rope(type, {128, 28, 2, 1}, 128, GGML_ROPE_TYPE_MROPE, 512, fs, ef, af, ff, v, fw)); // rope_multi,m-rope (qwen2vl 7B)
test_cases.emplace_back(new test_rope(type, { 80, 16, 2, 1}, 80, GGML_ROPE_TYPE_VISION, 512, fs, ef, af, ff, v, fw)); // rope_multi,m-rope (qwen2vl ViT)
}
test_cases.emplace_back(new test_rope(type, { 64, 128, 2, 1}, 64, 2, 512, fs, ef, af, ff, v)); // neox (falcon 40B)
test_cases.emplace_back(new test_rope(type, { 64, 128, 2, 1}, 64, 2, 512, fs, ef, af, ff, v, fw)); // neox (falcon 40B)
}
}