tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-07-07 15:52:53 +00:00
Code Issues Packages Projects Releases Wiki Activity

ggml : support bcast ggml_soft_max_ext, ggml_flash_attn_ext (#14435)

Browse Source 
ggml-ci
This commit is contained in:
Georgi Gerganov
2025-06-27 21:50:57 +03:00
parent 307e79d33d
commit ec68e84c32
11 changed files with 250 additions and 156 deletions
Download Patch File Download Diff File Expand all files Collapse all files

100
tests/test-backend-ops.cpp
View File

@ -2685,11 +2685,12 @@ struct test_soft_max : public test_case {
const std::array<int64_t, 4> ne;
const bool mask;
const ggml_type m_prec;
const std::array<int64_t, 2> nr23; // broadcast only dims 2 and 3
const float scale;
const float max_bias;
std::string vars() override {
return VARS_TO_STR6(type, ne, mask, m_prec, scale, max_bias);
return VARS_TO_STR7(type, ne, mask, m_prec, nr23, scale, max_bias);
}
// the 1024 test with bias occasionally fails:
@ -2702,18 +2703,19 @@ struct test_soft_max : public test_case {
std::array<int64_t, 4> ne = {10, 5, 4, 3},
bool mask = false,
ggml_type m_prec = GGML_TYPE_F32,
std::array<int64_t, 2> nr23 = {1, 1},
float scale = 1.0f,
float max_bias = 0.0f)
: type(type), ne(ne), mask(mask), m_prec(m_prec), scale(scale), max_bias(max_bias) {}
: type(type), ne(ne), mask(mask), m_prec(m_prec), nr23(nr23), scale(scale), max_bias(max_bias) {}
ggml_tensor * build_graph(ggml_context * ctx) override {
ggml_tensor * a = ggml_new_tensor(ctx, type, 4, ne.data());
ggml_tensor * a = ggml_new_tensor_4d(ctx, type, ne[0], ne[1], ne[2]*nr23[0], ne[3]*nr23[1]);
ggml_set_param(a);
ggml_set_name(a, "a");
ggml_tensor * mask = nullptr;
if (this->mask) {
mask = ggml_new_tensor_2d(ctx, m_prec, ne[0], ne[1]);
mask = ggml_new_tensor_4d(ctx, m_prec, ne[0], ne[1], ne[2], ne[3]);
ggml_set_name(mask, "mask");
}
@ -3544,7 +3546,7 @@ struct test_flash_attn_ext : public test_case {
const int64_t hsk; // K head size
const int64_t hsv; // V head size
const int64_t nh; // num heads
const int64_t nr; // repeat in Q, tests for grouped-query attention
const std::array<int64_t, 2> nr23; // repeat in dim 2 and 3, tests for grouped-query attention
const int64_t kv; // kv size
const int64_t nb; // batch size
@ -3558,7 +3560,7 @@ struct test_flash_attn_ext : public test_case {
std::array<int32_t, 4> permute;
std::string vars() override {
return VARS_TO_STR12(hsk, hsv, nh, nr, kv, nb, mask, max_bias, logit_softcap, prec, type_KV, permute);
return VARS_TO_STR12(hsk, hsv, nh, nr23, kv, nb, mask, max_bias, logit_softcap, prec, type_KV, permute);
}
double max_nmse_err() override {
@ -3569,13 +3571,13 @@ struct test_flash_attn_ext : public test_case {
GGML_UNUSED(t);
// Just counting matmul costs:
// Q*K^T is nb x hsk x kv, P*V is nb x kv x hsv, per head
return 2 * nh*nr * nb * (hsk + hsv) * kv;
return (2 * nh*nr23[0] * nb * (hsk + hsv) * kv)*nr23[1];
}
test_flash_attn_ext(int64_t hsk = 128, int64_t hsv = 128, int64_t nh = 32, int64_t nr = 1, int64_t kv = 96, int64_t nb = 8,
test_flash_attn_ext(int64_t hsk = 128, int64_t hsv = 128, int64_t nh = 32, std::array<int64_t, 2> nr23 = {1, 1}, int64_t kv = 96, int64_t nb = 8,
bool mask = true, float max_bias = 0.0f, float logit_softcap = 0.0f, ggml_prec prec = GGML_PREC_F32,
ggml_type type_KV = GGML_TYPE_F16, std::array<int32_t, 4> permute = {0, 1, 2, 3})
: hsk(hsk), hsv(hsv), nh(nh), nr(nr), kv(kv), nb(nb), mask(mask), max_bias(max_bias), logit_softcap(logit_softcap), prec(prec), type_KV(type_KV), permute(permute) {}
: hsk(hsk), hsv(hsv), nh(nh), nr23(nr23), kv(kv), nb(nb), mask(mask), max_bias(max_bias), logit_softcap(logit_softcap), prec(prec), type_KV(type_KV), permute(permute) {}
ggml_tensor * build_graph(ggml_context * ctx) override {
const int64_t hsk_padded = GGML_PAD(hsk, ggml_blck_size(type_KV));
@ -3594,18 +3596,18 @@ struct test_flash_attn_ext : public test_case {
return t;
};
ggml_tensor * q = create_permuted(GGML_TYPE_F32, hsk_padded, nb, nh*nr, 1);
ggml_tensor * q = create_permuted(GGML_TYPE_F32, hsk_padded, nb, nh*nr23[0], nr23[1]);
ggml_set_name(q, "q");
ggml_tensor * k = create_permuted(type_KV, hsk_padded, kv, nh, 1);
ggml_tensor * k = create_permuted(type_KV, hsk_padded, kv, nh, nr23[1]);
ggml_set_name(k, "k");
ggml_tensor * v = create_permuted(type_KV, hsv_padded, kv, nh, 1);
ggml_tensor * v = create_permuted(type_KV, hsv_padded, kv, nh, nr23[1]);
ggml_set_name(v, "v");
ggml_tensor * m = nullptr;
if (mask) {
m = ggml_new_tensor_4d(ctx, GGML_TYPE_F16, kv, GGML_PAD(nb, GGML_KQ_MASK_PAD), 1, 1);
m = ggml_new_tensor_4d(ctx, GGML_TYPE_F16, kv, GGML_PAD(nb, GGML_KQ_MASK_PAD), nr23[1], 1);
ggml_set_name(m, "m");
}
@ -4714,26 +4716,31 @@ static std::vector<std::unique_ptr<test_case>> make_test_cases_eval() {
for (int64_t ne1 : {16, 1024}) {
if (mask) {
for (ggml_type m_prec : {GGML_TYPE_F32, GGML_TYPE_F16}) {
test_cases.emplace_back(new test_soft_max(GGML_TYPE_F32, {ne0, ne1, 1, 1}, mask, m_prec, scale, max_bias));
test_cases.emplace_back(new test_soft_max(GGML_TYPE_F32, {ne0-1, ne1-1, 1, 1}, mask, m_prec, scale, max_bias));
test_cases.emplace_back(new test_soft_max(GGML_TYPE_F32, {ne0, ne1, 1, 1}, mask, m_prec, {1, 1}, scale, max_bias));
test_cases.emplace_back(new test_soft_max(GGML_TYPE_F32, {ne0-1, ne1-1, 1, 1}, mask, m_prec, {1, 1}, scale, max_bias));
if (ne0 <= 32 && ne1 <= 32) {
test_cases.emplace_back(new test_soft_max(GGML_TYPE_F32, {ne0, ne1, 1, 1}, mask, m_prec, {3, 1}, scale, max_bias));
test_cases.emplace_back(new test_soft_max(GGML_TYPE_F32, {ne0-1, ne1-1, 1, 1}, mask, m_prec, {2, 3}, scale, max_bias));
}
}
} else {
/* The precision of mask here doesn't matter as boolean mask is false */
test_cases.emplace_back(new test_soft_max(GGML_TYPE_F32, {ne0, ne1, 1, 1}, mask, GGML_TYPE_F32, scale, max_bias));
test_cases.emplace_back(new test_soft_max(GGML_TYPE_F32, {ne0-1, ne1-1, 1, 1}, mask, GGML_TYPE_F32, scale, max_bias));
test_cases.emplace_back(new test_soft_max(GGML_TYPE_F32, {ne0, ne1, 1, 1}, mask, GGML_TYPE_F32, {1, 1}, scale, max_bias));
test_cases.emplace_back(new test_soft_max(GGML_TYPE_F32, {ne0-1, ne1-1, 1, 1}, mask, GGML_TYPE_F32, {1, 1}, scale, max_bias));
}
}
}
}
}
}
test_cases.emplace_back(new test_soft_max(GGML_TYPE_F32, {16, 2, 32, 1}, true, GGML_TYPE_F32, 0.1f, 0.0f));
test_cases.emplace_back(new test_soft_max(GGML_TYPE_F32, {16, 2, 32, 1}, true, GGML_TYPE_F16, 0.1f, 0.0f));
test_cases.emplace_back(new test_soft_max(GGML_TYPE_F32, {16, 2, 32, 1}, false, GGML_TYPE_F32, 0.1f, 0.0f));
test_cases.emplace_back(new test_soft_max(GGML_TYPE_F32, {32, 2, 32, 1}, true, GGML_TYPE_F32, 0.1f, 0.0f));
test_cases.emplace_back(new test_soft_max(GGML_TYPE_F32, {32, 2, 32, 1}, true, GGML_TYPE_F16, 0.1f, 0.0f));
test_cases.emplace_back(new test_soft_max(GGML_TYPE_F32, {32, 2, 32, 1}, true, GGML_TYPE_F32, 0.1f, 8.0f));
test_cases.emplace_back(new test_soft_max(GGML_TYPE_F32, {32, 2, 32, 1}, true, GGML_TYPE_F16, 0.1f, 8.0f));
test_cases.emplace_back(new test_soft_max(GGML_TYPE_F32, {16, 2, 32, 1}, true, GGML_TYPE_F32, {1, 1}, 0.1f, 0.0f));
test_cases.emplace_back(new test_soft_max(GGML_TYPE_F32, {16, 2, 32, 1}, true, GGML_TYPE_F16, {1, 1}, 0.1f, 0.0f));
test_cases.emplace_back(new test_soft_max(GGML_TYPE_F32, {16, 2, 32, 1}, false, GGML_TYPE_F32, {1, 1}, 0.1f, 0.0f));
test_cases.emplace_back(new test_soft_max(GGML_TYPE_F32, {32, 2, 32, 1}, true, GGML_TYPE_F32, {1, 1}, 0.1f, 0.0f));
test_cases.emplace_back(new test_soft_max(GGML_TYPE_F32, {32, 2, 32, 1}, true, GGML_TYPE_F16, {1, 1}, 0.1f, 0.0f));
test_cases.emplace_back(new test_soft_max(GGML_TYPE_F32, {32, 2, 32, 1}, true, GGML_TYPE_F32, {1, 1}, 0.1f, 8.0f));
test_cases.emplace_back(new test_soft_max(GGML_TYPE_F32, {32, 2, 32, 1}, true, GGML_TYPE_F16, {1, 1}, 0.1f, 8.0f));
for (float max_bias : {0.0f, 8.0f}) {
for (float scale : {1.0f, 0.1f}) {
@ -4833,20 +4840,23 @@ static std::vector<std::unique_ptr<test_case>> make_test_cases_eval() {
for (float logit_softcap : {0.0f, 10.0f}) {
if (hsk != 128 && logit_softcap != 0.0f) continue;
for (int nh : { 4, }) {
for (int nr : { 1, 4, 16 }) {
if (nr == 16 && hsk != 128) continue;
for (int kv : { 512, 1024, }) {
if (nr != 1 && kv != 512) continue;
for (int nb : { 1, 3, 32, 35, }) {
for (ggml_prec prec : {GGML_PREC_F32, GGML_PREC_DEFAULT}) {
if (hsk != 128 && prec == GGML_PREC_DEFAULT) continue;
for (ggml_type type_KV : {GGML_TYPE_F16, GGML_TYPE_BF16, GGML_TYPE_Q8_0, GGML_TYPE_Q4_0}) {
test_cases.emplace_back(new test_flash_attn_ext(
hsk, hsv, nh, nr, kv, nb, mask, max_bias, logit_softcap, prec, type_KV));
// run fewer test cases permuted
if (mask == true && max_bias == 0.0f && logit_softcap == 0 && kv == 512) {
for (int nr3 : { 1, 3, }) {
if (hsk > 64 && nr3 > 1) continue; // skip broadcast for large head sizes
for (int nr2 : { 1, 4, 16 }) {
if (nr2 == 16 && hsk != 128) continue;
for (int kv : { 512, 1024, }) {
if (nr2 != 1 && kv != 512) continue;
for (int nb : { 1, 3, 32, 35, }) {
for (ggml_prec prec : {GGML_PREC_F32, GGML_PREC_DEFAULT}) {
if (hsk != 128 && prec == GGML_PREC_DEFAULT) continue;
for (ggml_type type_KV : {GGML_TYPE_F16, GGML_TYPE_BF16, GGML_TYPE_Q8_0, GGML_TYPE_Q4_0}) {
test_cases.emplace_back(new test_flash_attn_ext(
hsk, hsv, nh, nr, kv, nb, mask, max_bias, logit_softcap, prec, type_KV, {0, 2, 1, 3}));
hsk, hsv, nh, {nr2, nr3}, kv, nb, mask, max_bias, logit_softcap, prec, type_KV));
// run fewer test cases permuted
if (mask == true && max_bias == 0.0f && logit_softcap == 0 && kv == 512) {
test_cases.emplace_back(new test_flash_attn_ext(
hsk, hsv, nh, {nr2, nr3}, kv, nb, mask, max_bias, logit_softcap, prec, type_KV, {0, 2, 1, 3}));
}
}
}
}
@ -4890,13 +4900,13 @@ static std::vector<std::unique_ptr<test_case>> make_test_cases_perf() {
test_cases.emplace_back(new test_cpy(GGML_TYPE_F32, GGML_TYPE_F32, {8192, 512, 2, 1}, {0, 2, 1, 3}));
test_cases.emplace_back(new test_cpy(GGML_TYPE_F32, GGML_TYPE_F32, {3072, 512, 2, 1}, {0, 2, 1, 3}));
test_cases.emplace_back(new test_soft_max(GGML_TYPE_F32, {4096, 4096, 5, 1}, false, GGML_TYPE_F32, 1.0f, 0.0f));
test_cases.emplace_back(new test_soft_max(GGML_TYPE_F32, {77, 4096, 5, 1}, false, GGML_TYPE_F32, 1.0f, 0.0f));
test_cases.emplace_back(new test_soft_max(GGML_TYPE_F32, {1024, 1024, 10, 1}, false, GGML_TYPE_F32, 1.0f, 0.0f));
test_cases.emplace_back(new test_soft_max(GGML_TYPE_F32, {77, 1024, 10, 1}, false, GGML_TYPE_F32, 1.0f, 0.0f));
test_cases.emplace_back(new test_soft_max(GGML_TYPE_F32, {256, 256, 20, 1}, false, GGML_TYPE_F32, 1.0f, 0.0f));
test_cases.emplace_back(new test_soft_max(GGML_TYPE_F32, {64, 64, 20, 1}, false, GGML_TYPE_F32, 1.0f, 0.0f));
test_cases.emplace_back(new test_soft_max(GGML_TYPE_F32, {77, 64, 20, 1}, false, GGML_TYPE_F32, 1.0f, 0.0f));
test_cases.emplace_back(new test_soft_max(GGML_TYPE_F32, {4096, 4096, 5, 1}, false, GGML_TYPE_F32, {1, 1}, 1.0f, 0.0f));
test_cases.emplace_back(new test_soft_max(GGML_TYPE_F32, {77, 4096, 5, 1}, false, GGML_TYPE_F32, {1, 1}, 1.0f, 0.0f));
test_cases.emplace_back(new test_soft_max(GGML_TYPE_F32, {1024, 1024, 10, 1}, false, GGML_TYPE_F32, {1, 1}, 1.0f, 0.0f));
test_cases.emplace_back(new test_soft_max(GGML_TYPE_F32, {77, 1024, 10, 1}, false, GGML_TYPE_F32, {1, 1}, 1.0f, 0.0f));
test_cases.emplace_back(new test_soft_max(GGML_TYPE_F32, {256, 256, 20, 1}, false, GGML_TYPE_F32, {1, 1}, 1.0f, 0.0f));
test_cases.emplace_back(new test_soft_max(GGML_TYPE_F32, {64, 64, 20, 1}, false, GGML_TYPE_F32, {1, 1}, 1.0f, 0.0f));
test_cases.emplace_back(new test_soft_max(GGML_TYPE_F32, {77, 64, 20, 1}, false, GGML_TYPE_F32, {1, 1}, 1.0f, 0.0f));
test_cases.emplace_back(new test_argmax(GGML_TYPE_F32, {32, 10, 1, 1}));
test_cases.emplace_back(new test_argmax(GGML_TYPE_F32, {1024, 10, 1, 1}));
@ -4928,7 +4938,7 @@ static std::vector<std::unique_ptr<test_case>> make_test_cases_perf() {
for (int kv : { 4096, 8192, 16384, }) {
for (int hs : { 64, 128, }) {
for (int nr : { 1, 4, }) {
test_cases.emplace_back(new test_flash_attn_ext(hs, hs, 8, nr, kv, 1, true, 0, 0, GGML_PREC_F32, GGML_TYPE_F16));
test_cases.emplace_back(new test_flash_attn_ext(hs, hs, 8, {nr, 1}, kv, 1, true, 0, 0, GGML_PREC_F32, GGML_TYPE_F16));
}
}
}