LLM-Inference/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-08-12 22:31:11 +04:00
Code Issues Packages Projects Releases Wiki Activity

Test support for alternative conv layout (#25617)

Browse Source 
* add  bool cwhn = true to conv_2d test cases

* add layout check at graph building time

* extend layout checks for conv2d.cu kernel

* in CPU back-end kernel needs to be stored contiguously to prevent test failures with cwhn=1

* trim white space

* do op support check in vulkan backend

* fix CI failure and vulkan run-time assert failure by introducing new graph build-time check in ggml_backend_vk_device_supports_op

* add additional check in support_op function for Vulkan to fix run-time assert failure
This commit is contained in:
pmaybank
2026-07-31 01:14:16 +08:00
committed by GitHub
parent 432d7ffe2c
commit 958d9c0b61
5 changed files with 26 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-cpu/ggml-cpu.cpp
+2
View File
@@ -469,6 +469,8 @@ static bool ggml_backend_cpu_device_supports_op(ggml_backend_dev_t dev, const st
return (src0->type == GGML_TYPE_F32 ||
((src0->type == GGML_TYPE_F16 || ggml_is_quantized(src0->type)) && src0->ne[2] == src1->ne[2] && src0->ne[3] == src1->ne[3])) &&
src1->type == GGML_TYPE_F32 && op->type == GGML_TYPE_F32;
case GGML_OP_CONV_2D:
return ggml_is_contiguous(op->src[0]);
default:
return true;
}
ggml/src/ggml-cuda/conv2d.cu
+1
View File
@@ -126,6 +126,7 @@ void ggml_cuda_op_conv2d(ggml_backend_cuda_context & ctx, ggml_tensor * dst) {
const float * X_D = (const float *) input->data;
float * Y_D = (float *) dst->data;
GGML_ASSERT(ggml_is_contiguous(input));
GGML_ASSERT(ggml_is_contiguous(kernel));
GGML_ASSERT(kernel->type == GGML_TYPE_F16 || kernel->type == GGML_TYPE_F32);
ggml/src/ggml-cuda/ggml-cuda.cu
+1 -1
View File
@@ -5105,7 +5105,7 @@ static bool ggml_backend_cuda_device_supports_op(ggml_backend_dev_t dev, const g
case GGML_OP_IM2COL:
case GGML_OP_IM2COL_3D:
case GGML_OP_CONV_2D:
return true;
return (ggml_is_contiguous(op->src[0]) && ggml_is_contiguous(op->src[1]));
case GGML_OP_CONV_2D_DW:
return op->src[0]->type == GGML_TYPE_F32;
case GGML_OP_CONV_TRANSPOSE_2D:
ggml/src/ggml-vulkan/ggml-vulkan.cpp
+7
View File
@@ -18016,10 +18016,17 @@ static bool ggml_backend_vk_device_supports_op(ggml_backend_dev_t dev, const ggm
case GGML_OP_CONV_2D:
case GGML_OP_CONV_TRANSPOSE_2D:
{
const bool transpose = op->op == GGML_OP_CONV_TRANSPOSE_2D;
const int64_t cout = !transpose ? op->src[0]->ne[3] : op->src[0]->ne[2];
const int64_t cin = !transpose ? op->src[0]->ne[2] : op->src[0]->ne[3];
// Channel-contiguous format is not supported yet.
return ((op->src[0]->type == GGML_TYPE_F32 || op->src[0]->type == GGML_TYPE_F16) &&
(op->src[0]->nb[0] == sizeof(float) || op->src[0]->nb[0] == sizeof(ggml_fp16_t) ) &&
op->src[1]->type == GGML_TYPE_F32 &&
op->type == GGML_TYPE_F32 &&
cout == op->ne[2] &&
cin == op->src[1]->ne[2] &&
ggml_is_contiguous(op->src[0]) &&
ggml_is_contiguous(op->src[1]) &&
ggml_is_contiguous(op));
tests/test-backend-ops.cpp
+15 -4
View File
@@ -8329,7 +8329,11 @@ static std::vector<std::unique_ptr<test_case>> make_test_cases_eval() {
test_cases.emplace_back(new test_conv_2d(
{ act_case[iwh_idx], act_case[iwh_idx], act_case[Cin_idx], act_case[B_idx] },
{ act_case[kwh_idx], act_case[kwh_idx], act_case[Cin_idx], act_case[Cout_idx] },
kernel_type, 1, 1, 0, 0, 1, 1, false));
kernel_type, 1, 1, 0, 0, 1, 1, false)); // bool cwhn = false
test_cases.emplace_back(new test_conv_2d(
{ act_case[iwh_idx], act_case[iwh_idx], act_case[Cin_idx], act_case[B_idx] },
{ act_case[kwh_idx], act_case[kwh_idx], act_case[Cin_idx], act_case[Cout_idx] },
kernel_type, 1, 1, 0, 0, 1, 1, true)); // bool cwhn = true
}
}
#endif
@@ -8358,7 +8362,9 @@ static std::vector<std::unique_ptr<test_case>> make_test_cases_eval() {
calc_conv_output_size(H, KH, s1, p1, d1) > 0) {
for (auto kernel_type : {GGML_TYPE_F32, GGML_TYPE_F16}) {
test_cases.emplace_back(new test_conv_2d(
{ W, H, Cin, 2 }, { KW, KH, Cin, Cout }, kernel_type, s0, s1, p0, p1, d0, d1, false));
{ W, H, Cin, 2 }, { KW, KH, Cin, Cout }, kernel_type, s0, s1, p0, p1, d0, d1, false)); // bool cwhn = false
test_cases.emplace_back(new test_conv_2d(
{ W, H, Cin, 2 }, { KW, KH, Cin, Cout }, kernel_type, s0, s1, p0, p1, d0, d1, true)); // bool cwhn = true
}
}
}
@@ -8370,7 +8376,8 @@ static std::vector<std::unique_ptr<test_case>> make_test_cases_eval() {
}
}
for (auto kernel_type : {GGML_TYPE_F32, GGML_TYPE_F16}) {
test_cases.emplace_back(new test_conv_2d({ 256, 256, 192, 1 }, { 3, 3, 192, 96 }, kernel_type, 1, 1, 1, 1, 1, 1, false));
test_cases.emplace_back(new test_conv_2d({ 256, 256, 192, 1 }, { 3, 3, 192, 96 }, kernel_type, 1, 1, 1, 1, 1, 1, false)); // bool cwhn = false
test_cases.emplace_back(new test_conv_2d({ 256, 256, 192, 1 }, { 3, 3, 192, 96 }, kernel_type, 1, 1, 1, 1, 1, 1, true)); // bool cwhn = true
}
// sycl backend will limit task global_range < MAX_INT
@@ -9757,7 +9764,11 @@ static std::vector<std::unique_ptr<test_case>> make_test_cases_perf() {
test_cases.emplace_back(new test_conv_2d(
{ act_case[iwh_idx], act_case[iwh_idx], act_case[Cin_idx], act_case[B_idx] },
{ act_case[kwh_idx], act_case[kwh_idx], act_case[Cin_idx], act_case[Cout_idx] },
kernel_type, 1, 1, 0, 0, 1, 1, false));
kernel_type, 1, 1, 0, 0, 1, 1, false)); // bool cwhn = false
test_cases.emplace_back(new test_conv_2d(
{ act_case[iwh_idx], act_case[iwh_idx], act_case[Cin_idx], act_case[B_idx] },
{ act_case[kwh_idx], act_case[kwh_idx], act_case[Cin_idx], act_case[Cout_idx] },
kernel_type, 1, 1, 0, 0, 1, 1, true)); // bool cwhn = true
}
}