vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-13 10:29:43 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

vulkan : fix out-of-bounds access in argmax kernel (#15342)

Browse source 
ggml-ci
This commit is contained in:
Georgi Gerganov 2025-08-15 17:16:36 +03:00 • committed by GitHub
parent db3010bd23
commit 5edf1592fd
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 15 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

2
ggml/src/ggml-vulkan/ggml-vulkan.cpp
View file

@ -8392,7 +8392,7 @@ static void ggml_vk_sum_rows(ggml_backend_vk_context * ctx, vk_context& subctx,
}
static void ggml_vk_argmax(ggml_backend_vk_context * ctx, vk_context& subctx, const ggml_tensor * src0, ggml_tensor * dst, bool dryrun = false) {
ggml_vk_op_f32<vk_op_push_constants>(ctx, subctx, src0, nullptr, nullptr, dst, GGML_OP_ARGMAX, { (uint32_t)src0->ne[0], 0, 0.0f, 0.0f }, dryrun);
ggml_vk_op_f32<vk_op_push_constants>(ctx, subctx, src0, nullptr, nullptr, dst, GGML_OP_ARGMAX, { (uint32_t)src0->ne[0], (uint32_t)src0->ne[1], 0.0f, 0.0f }, dryrun);
}
static void ggml_vk_count_equal(ggml_backend_vk_context * ctx, vk_context& subctx, const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst, bool dryrun = false) {

17
ggml/src/ggml-vulkan/vulkan-shaders/argmax.comp
View file

@ -5,6 +5,8 @@
#extension GL_EXT_control_flow_attributes : enable
#define FLT_MAX 3.402823466e+38F
layout(local_size_x_id = 0, local_size_y = 1, local_size_z = 1) in;
layout (binding = 0) readonly buffer A {A_TYPE data_a[];};
@ -19,19 +21,26 @@ void main() {
const uint row = gl_WorkGroupID.z * 262144 + gl_WorkGroupID.y * 512 + gl_WorkGroupID.x;
const uint col = gl_LocalInvocationID.x;
if (col >= p.KX) {
if (row >= p.KY) {
return;
}
A_TYPE amax = data_a[row*p.KX + col];
tmp[col] = col;
A_TYPE amax = -FLT_MAX;
uint acol = col;
if (col < p.KX) {
amax = data_a[row*p.KX + col];
}
for (uint i = col + BLOCK_SIZE; i < p.KX; i += BLOCK_SIZE) {
A_TYPE val = data_a[row*p.KX + i];
if (val > amax) {
amax = val;
tmp[col] = i;
acol = i;
}
}
tmp[col] = acol;
tmpmax[col] = amax;
barrier();

1
tests/test-backend-ops.cpp
View file

@ -5528,6 +5528,7 @@ static std::vector<std::unique_ptr<test_case>> make_test_cases_eval() {
test_cases.emplace_back(new test_count_equal(GGML_TYPE_F32, {4, 5000, 1, 1}));
test_cases.emplace_back(new test_argmax(GGML_TYPE_F32, {32, 1, 1, 1}));
test_cases.emplace_back(new test_argmax(GGML_TYPE_F32, {32, 513, 1, 1}));
test_cases.emplace_back(new test_argmax(GGML_TYPE_F32, {100, 10, 1, 1}));
test_cases.emplace_back(new test_argmax(GGML_TYPE_F32, {1024, 10, 1, 1}));
test_cases.emplace_back(new test_argmax(GGML_TYPE_F32, {1024, 12, 1, 1}));