Skip to content

Fix error in decoder cache #26

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
wine99 merged 1 commit into from
Dec 5, 2025
Merged

Fix error in decoder cache #26

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
2 changes: 1 addition & 1 deletion ggml/src/ggml-openvino/ggml-decoder.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -210,10 +210,10 @@ class GgmlOvDecoder : public ov::frontend::ggml::GgmlDecoder {
static std::vector<size_t> get_stride(const ggml_tensor * tensor);
static ov::element::Type get_ov_type(const ggml_tensor * tensor);
static std::string compute_op_type(const ggml_tensor * node);
void add_extra_inputs();

private:
void set_input_output(ggml_tensor * node, bool naive = false);
void add_extra_inputs();
int compute_op_case(const ggml_tensor * node) const;

void validate_cgraph() const;
Expand Down
6 changes: 4 additions & 2 deletions ggml/src/ggml-openvino/utils.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -102,8 +102,10 @@ enum ggml_status ov_graph_compute_dynamic(ggml_cgraph * cgraph, const std::strin

if (cache_hit) {
std::map<std::string, std::shared_ptr<ov::Node>> model_weights;
ggml_decoder = std::make_shared<GgmlOvDecoder>(cgraph, m_params, c_params, model_weights, is_static);
decoder_cache[key] = ggml_decoder;
ggml_decoder = decoder_cache[key];
ggml_decoder->set_compute_params(c_params);
ggml_decoder->set_model_params(m_params);
ggml_decoder->add_extra_inputs();
infer_request = infer_request_cache[key];

decoder_end_time = ggml_time_us();
Expand Down