Skip to content

cuda : update supports_op for matrix multiplication #8245

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
Jul 2, 2024
Merged

cuda : update supports_op for matrix multiplication #8245

Show file tree
Hide file tree
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
47 changes: 30 additions & 17 deletions ggml/src/ggml-cuda.cu
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2711,27 +2711,40 @@ GGML_CALL static bool ggml_backend_cuda_supports_op(ggml_backend_t backend, cons
case GGML_OP_MUL_MAT:
case GGML_OP_MUL_MAT_ID:
{
struct ggml_tensor * a;
struct ggml_tensor * b;
struct ggml_tensor * a = op->src[0];
if (op->op == GGML_OP_MUL_MAT) {
a = op->src[0];
b = op->src[1];
} else {
a = op->src[2];
b = op->src[1];
}
if (a->ne[3] != b->ne[3]) {
return false;
}
ggml_type a_type = a->type;
if (a_type == GGML_TYPE_IQ2_XXS || a_type == GGML_TYPE_IQ2_XS || a_type == GGML_TYPE_IQ3_XXS ||
a_type == GGML_TYPE_IQ1_S || a_type == GGML_TYPE_IQ4_NL || a_type == GGML_TYPE_IQ3_S ||
a_type == GGML_TYPE_IQ1_M || a_type == GGML_TYPE_IQ2_S || a_type == GGML_TYPE_IQ4_XS) {
if (b->ne[1] == 1 && ggml_nrows(b) > 1) {
struct ggml_tensor * b = op->src[1];
if (a->ne[3] != b->ne[3]) {
return false;
}
}
return true;
switch (a->type) {
case GGML_TYPE_F32:
case GGML_TYPE_F16:
case GGML_TYPE_Q4_0:
case GGML_TYPE_Q4_1:
case GGML_TYPE_Q5_0:
case GGML_TYPE_Q5_1:
case GGML_TYPE_Q8_0:
case GGML_TYPE_Q2_K:
case GGML_TYPE_Q3_K:
case GGML_TYPE_Q4_K:
case GGML_TYPE_Q5_K:
case GGML_TYPE_Q6_K:
case GGML_TYPE_Q8_K:
case GGML_TYPE_IQ1_M:
case GGML_TYPE_IQ1_S:
case GGML_TYPE_IQ2_S:
case GGML_TYPE_IQ2_XS:
case GGML_TYPE_IQ2_XXS:
case GGML_TYPE_IQ3_S:
case GGML_TYPE_IQ3_XXS:
case GGML_TYPE_IQ4_NL:
case GGML_TYPE_IQ4_XS:
return true;
default:
return false;
}
} break;
case GGML_OP_GET_ROWS:
{
Expand Down
1 change: 1 addition & 0 deletions tests/test-backend-ops.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2052,6 +2052,7 @@ static bool test_backend(ggml_backend_t backend, test_mode mode, const char * op
GGML_TYPE_IQ2_XS, GGML_TYPE_IQ2_S,
GGML_TYPE_IQ3_XXS, GGML_TYPE_IQ1_S, GGML_TYPE_IQ1_M,
GGML_TYPE_IQ4_NL, GGML_TYPE_IQ3_S, GGML_TYPE_IQ4_XS,
GGML_TYPE_BF16,
};

// unary ops
Expand Down
Loading