Skip to content

[GPU] Use correct type for variable #30122

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 3 commits into from
Apr 15, 2025
Merged

[GPU] Use correct type for variable #30122

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
17ebb5a
[GPU] Use correct type for variable
davidsnam-intel Apr 14, 2025
6783b42
Prevent loss of data by static casting
davidsnam-intel Apr 14, 2025
1edf1b9
Use OPENVINO_ASSERT instead of if-throw
davidsnam-intel Apr 15, 2025
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
2 changes: 1 addition & 1 deletion src/plugins/intel_gpu/src/kernel_selector/kernel_selector_params.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -543,7 +543,7 @@ struct FusedOpsConfiguration {
FusedOpsConfiguration& SetShuffleVarName(std::string val) { shuffle_var_name = val; return *this; }
bool IsPostReorderFused(void) const { return orig_output_layout != DataLayout::DataLayoutCount; }
int GetDimIndexFromOrder(Tensor::DataChannelName val) const {
size_t dims_num = bfzyx_idx_order.size();
int dims_num = static_cast<int>(bfzyx_idx_order.size());
if (val == Tensor::DataChannelName::BATCH && dims_num >= 1) {
return 0;
} else if (val == Tensor::DataChannelName::FEATURE && dims_num >= 2) {
Expand Down
3 changes: 2 additions & 1 deletion ...gpu/src/kernel_selector/kernels/dynamic_quantize/dynamic_quantize_kernel_opt_kv_cache.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -118,8 +118,9 @@ JitConstants DynamicQuantizeKernelKVCache::GetJitConstants(const dynamic_quantiz

const auto& input_dims = get_normalized_dims(params.inputs[0]);
const auto total_grouped_elements = get_elements_number_per_group(params);
const auto per_iter_elements_number = get_per_iter_elements_number(params);
const auto total_subgroups_number = total_grouped_elements / input_dims.back().v;
const auto per_iter_elements_number = get_per_iter_elements_number(params);
OPENVINO_ASSERT(per_iter_elements_number > 0, "[GPU] per_iter_elements_number is zero, division by zero would occur.");

// Drop the last dimensions, since it will be processed in the kernel's loop
grouped_dims.pop_back();
Expand Down
4 changes: 2 additions & 2 deletions src/plugins/intel_gpu/src/plugin/transformations_pipeline.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1112,8 +1112,8 @@ void TransformationsPipeline::apply(std::shared_ptr<ov::Model> func) {
manager.register_pass<ov::intel_gpu::MoveFCReshapeToWeights>();
manager.register_pass<ov::intel_gpu::ConvertFullyConnectedToFullyConnectedCompressed>();

bool disable_horizontal_fc_fusion = GPU_DEBUG_VALUE_OR(config.get_disable_horizontal_fc_fusion(), false);
bool disable_fc_swiglu_fusion = GPU_DEBUG_VALUE_OR(config.get_disable_fc_swiglu_fusion(), false);
const bool disable_horizontal_fc_fusion = GPU_DEBUG_VALUE_OR(config.get_disable_horizontal_fc_fusion(), false);
const bool disable_fc_swiglu_fusion = GPU_DEBUG_VALUE_OR(config.get_disable_fc_swiglu_fusion(), false);

// mlp fusion is only supported for cldnn on high performant GPUis
bool fuse_mlp_swiglu = !device_info.supports_immad &&
Expand Down
Loading