Skip to content

ggml-openvino : fix clangd and MSVC warnings, enforce internal linkage #320

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
ravi9 merged 2 commits into from
Sep 17, 2026
Merged

ggml-openvino : fix clangd and MSVC warnings, enforce internal linkage #320

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
4029053
ggml-openvino : fix clangd and MSVC warnings
mostafafaheem Sep 16, 2026
6669627
fix int to ptr cast, more internal linkage enforcement, and avoiding …
mostafafaheem Sep 16, 2026
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
23 changes: 10 additions & 13 deletions ggml/src/ggml-openvino/ggml-decoder.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -245,7 +245,7 @@ void GgmlOvDecoder::set_input_output() {
if (src->op == GGML_OP_VIEW) {
// Traverse upward through nested VIEW operations
std::remove_reference_t<decltype(current_node_info.node_inputs_views[src_name])> view_chain;
auto current = src;
auto * current = src;

while (current != nullptr) {
auto current_name = get_tensor_ov_name(m_cgraph, current);
Expand Down Expand Up @@ -612,9 +612,8 @@ std::pair<ModelParams, ComputeParams> GgmlOvDecoder::compute_llm_params(ggml_cgr
if (node->src[1]->view_src != nullptr) {
if (node->src[3] != nullptr) {
return 4; // decoder self-attention
} else {
return 5; // cross-attention or encoder self-attention
};
}
return 5; // cross-attention or encoder self-attention
}
break;
default:
Expand Down Expand Up @@ -736,8 +735,7 @@ std::pair<ModelParams, ComputeParams> GgmlOvDecoder::compute_llm_params(ggml_cgr

bool rope_seen = false;
for (int i = 0; i < cgraph->n_nodes; i++) {
auto * node = cgraph->nodes[i];
std::string name = std::string(node->name);
ggml_tensor * node = cgraph->nodes[i];
const int attention_pattern_case = get_attention_pattern_case(node);
if (attention_pattern_case != -1) {
ggml_tensor * cache_k_permute = nullptr;
Expand Down Expand Up @@ -948,7 +946,6 @@ ov::PartialShape GgmlOvDecoder::get_graph_input_shape(const ggml_tensor * op,
if (m_naive) {
return input != nullptr ? ov::PartialShape{get_shape(input)} : ov::PartialShape{get_shape(op)};
}
auto name = std::string(input->name);
ov::PartialShape input_shape;

if (is_inp_tok(input, op) || is_inp_pos(input, op)) {
Expand Down Expand Up @@ -1474,7 +1471,7 @@ std::shared_ptr<ov::Node> GgmlOvDecoder::create_weight_node(ggml_tensor * tensor
void GgmlOvDecoder::dump_cgraph(const ggml_cgraph * cgraph, std::string & filename) {
std::ofstream file(filename);
if (!file.is_open()) {
std::cerr << "Failed to open file" << std::endl;
std::cerr << "Failed to open file" << '\n';
return;
}

Expand Down Expand Up @@ -1580,11 +1577,11 @@ void print_tensor_address_map(const ggml_cgraph * cgraph) {
}
}
for (const auto & pair : address_map) {
std::cout << "Address: " << pair.first << std::endl;
std::cout << "Address: " << pair.first << '\n';
for (const auto & name : pair.second) {
std::cout << name << " ; ";
}
std::cout << std::endl << std::endl;
std::cout << "\n\n";
}
}

Expand Down Expand Up @@ -2226,7 +2223,7 @@ void GgmlOvDecoder::compute_node_dynamic_dims() {
std::cout << ", ";
}
}
std::cout << "]" << std::endl;
std::cout << "]" << '\n';
// print the src name & shape with the dynamic dim for debugging
for (int j = 0; j < GGML_MAX_SRC; j++) {
ggml_tensor * src = node->src[j];
Expand All @@ -2245,9 +2242,9 @@ void GgmlOvDecoder::compute_node_dynamic_dims() {
std::cout << ", ";
}
}
std::cout << "]" << std::endl;
std::cout << "]" << '\n';
}
std::cout << std::endl;
std::cout << '\n';
}
}
}
26 changes: 12 additions & 14 deletions ggml/src/ggml-openvino/ggml-decoder.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -354,70 +354,70 @@ class GgmlOvDecoder : public ov::frontend::ggml::GgmlDecoder {

void update_io(ggml_cgraph * cgraph);

inline static bool is_inp_tok(const ggml_tensor * tensor, const ggml_tensor * op) {
static bool is_inp_tok(const ggml_tensor * tensor, const ggml_tensor * op) {
return op->op == GGML_OP_GET_ROWS && tensor == op->src[1] && op->src[0]->op == GGML_OP_NONE;
}

inline static bool is_inp_pos(const ggml_tensor * tensor, const ggml_tensor * op) {
static bool is_inp_pos(const ggml_tensor * tensor, const ggml_tensor * op) {
return op->op == GGML_OP_ROPE && tensor == op->src[1];
}

// IMROPE packs 4 stacked position planes (t/h/w/e) into inp_pos, each of length
// n_tokens; other modes carry a single position per token.
inline static int get_inp_pos_n_planes(const ggml_tensor * op) {
static int get_inp_pos_n_planes(const ggml_tensor * op) {
return op->op_params[2] == GGML_ROPE_TYPE_IMROPE ? 4 : 1;
}

inline static bool is_inp_emb(const ggml_tensor * tensor, const ggml_tensor * op) {
static bool is_inp_emb(const ggml_tensor * tensor, const ggml_tensor * op) {
return tensor->op == GGML_OP_GET_ROWS && op->op == GGML_OP_RMS_NORM;
}

inline static bool is_inp_mask(const ggml_tensor * tensor, const ggml_tensor * op) {
static bool is_inp_mask(const ggml_tensor * tensor, const ggml_tensor * op) {
return op->op == GGML_OP_CPY || (op->op == GGML_OP_FLASH_ATTN_EXT && tensor == op->src[3]) ||
(op->op == GGML_OP_SOFT_MAX && tensor == op->src[1]);
}

inline static bool is_inp_mean(const ggml_tensor * tensor, const ggml_tensor * op) {
static bool is_inp_mean(const ggml_tensor * tensor, const ggml_tensor * op) {
return op->op == GGML_OP_MUL_MAT && tensor == op->src[1] && tensor->op == GGML_OP_NONE &&
(tensor->flags & GGML_TENSOR_FLAG_INPUT) && tensor->type == GGML_TYPE_F32 &&
op->src[0] != nullptr && op->src[0]->op != GGML_OP_NONE;
}

inline static bool is_rope_freqs_weight(const ggml_tensor * tensor, const ggml_tensor * op) {
static bool is_rope_freqs_weight(const ggml_tensor * tensor, const ggml_tensor * op) {
return op->op == GGML_OP_ROPE && tensor == op->src[2];
}

// also returns true for cache_s and cache_r in SSM/DeltaNet models
inline static bool is_kvcache(const ggml_tensor * tensor, const ggml_tensor * op) {
static bool is_kvcache(const ggml_tensor * tensor, const ggml_tensor * op) {
if (tensor == nullptr) {
return false;
}
return (tensor->buffer != nullptr && tensor->buffer->usage == GGML_BACKEND_BUFFER_USAGE_ANY) ||
(op != nullptr && op->op == GGML_OP_SET_ROWS && op->src[2] == tensor);
}

inline static bool is_conv_state_writeback(const ggml_tensor * node) {
static bool is_conv_state_writeback(const ggml_tensor * node) {
return node->op == GGML_OP_CPY && node->view_src != nullptr && is_kvcache(node->view_src, nullptr) &&
node->src[0] != nullptr && node->src[0]->op == GGML_OP_VIEW && node->src[0]->src[0] != nullptr &&
node->src[0]->src[0]->op == GGML_OP_CONCAT && node->src[1] != nullptr &&
node->src[1]->op == GGML_OP_VIEW && node->src[1]->view_src == node->view_src;
}

inline static bool is_kv_idx(const ggml_tensor * tensor, const ggml_tensor * op) {
static bool is_kv_idx(const ggml_tensor * tensor, const ggml_tensor * op) {
return op->op == GGML_OP_SET_ROWS && op->src[1] == tensor;
}

bool is_swa_mask(const ggml_tensor * tensor) const {
return m_model_params.swa_mask != nullptr && tensor == m_model_params.swa_mask;
}

inline static bool is_output_idx(const ggml_tensor * tensor, const ggml_tensor * op) {
static bool is_output_idx(const ggml_tensor * tensor, const ggml_tensor * op) {
return op->op == GGML_OP_GET_ROWS && tensor == op->src[1] && op->src[0]->op != GGML_OP_NONE &&
op->src[1]->op == GGML_OP_NONE;
}

// the state permutation index input used in SSM/DeltaNet models (inp->s_copy in llama-graph.cpp)
inline static bool is_inp_s_copy(const ggml_tensor * tensor, const ggml_tensor * op) {
static bool is_inp_s_copy(const ggml_tensor * tensor, const ggml_tensor * op) {
return op->op == GGML_OP_GET_ROWS && tensor == op->src[1] &&
op->src[0]->buffer->usage == GGML_BACKEND_BUFFER_USAGE_ANY;
}
Expand Down Expand Up @@ -481,5 +481,3 @@ class GgmlOvDecoder : public ov::frontend::ggml::GgmlDecoder {
};

void print_tensor_address_map(const ggml_cgraph * cgraph);

std::optional<int> extract_layer_from_name(const std::string & name);
4 changes: 0 additions & 4 deletions ggml/src/ggml-openvino/ggml-openvino-extra.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -472,10 +472,6 @@ ggml_openvino_extracted_layout ggml_openvino_get_extracted_layout(const ggml_ten

switch (tensor->type) {
case GGML_TYPE_MXFP4:
layout.is_u4 = true;
layout.is_symmetric = true;
break;

case GGML_TYPE_Q4_0:
layout.is_u4 = true;
layout.is_symmetric = true;
Expand Down
31 changes: 17 additions & 14 deletions ggml/src/ggml-openvino/ggml-openvino.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,12 +28,7 @@
#include <string>
#include <vector>

#ifndef _WIN32
# include <sys/mman.h>
# include <unistd.h>
#endif

#if defined(_WIN32)
#ifdef _WIN32
# define WIN32_LEAN_AND_MEAN
# ifndef NOMINMAX
# define NOMINMAX
Expand Down Expand Up @@ -61,6 +56,7 @@
// - CPU repack buffer: tensor->extra stores tensor_traits with repacked data
// =====================================================

namespace {
// Buffer context that manages per-tensor allocations (no contiguous buffer for weights)
struct ggml_backend_openvino_buffer_context {
int device;
Expand Down Expand Up @@ -199,6 +195,7 @@ struct ggml_backend_openvino_buffer_type_context {
int device;
std::string name;
};
} // namespace

// =====================================================
// Host weight-buffer release (GGML_OPENVINO_RELEASE_WEIGHTS)
Expand Down Expand Up @@ -258,14 +255,16 @@ void ggml_openvino_release_weight_buffers() {
for (const auto & b : reg.buffers) {
// Align down/up to page boundaries so madvise only drops whole pages
// fully owned by this buffer.
const long page = sysconf(_SC_PAGESIZE);
uintptr_t start = reinterpret_cast<uintptr_t>(b.first);
uintptr_t end = start + b.second;
uintptr_t astart = (start + page - 1) & ~(uintptr_t) (page - 1);
uintptr_t aend = end & ~(uintptr_t) (page - 1);
if (aend > astart) {
if (madvise(reinterpret_cast<void *>(astart), aend - astart, MADV_DONTNEED) == 0) {
total += aend - astart;
const size_t page = (size_t) sysconf(_SC_PAGESIZE);
const uintptr_t ustart = reinterpret_cast<uintptr_t>(b.first);
const size_t offset_to_page = (page - (ustart & (page - 1))) & (page - 1);
if (b.second > offset_to_page) {
const size_t aligned_len = (b.second - offset_to_page) & ~(page - 1);
if (aligned_len > 0) {
char * astart = static_cast<char *>(b.first) + offset_to_page;
if (madvise(astart, aligned_len, MADV_DONTNEED) == 0) {
total += aligned_len;
}
}
}
}
Expand Down Expand Up @@ -876,11 +875,13 @@ GGML_BACKEND_API bool ggml_backend_is_openvino(ggml_backend_t backend) {
return backend != NULL && ggml_guid_matches(backend->guid, ggml_backend_openvino_guid());
}

namespace {
struct ggml_backend_openvino_device_context {
int device;
std::string name;
std::string description;
};
}

static const char * ggml_backend_openvino_device_get_name(ggml_backend_dev_t dev) {
ggml_backend_openvino_device_context * ctx = (ggml_backend_openvino_device_context *) dev->context;
Expand Down Expand Up @@ -1588,9 +1589,11 @@ static const struct ggml_backend_device_i ggml_backend_openvino_device_interface
/* .event_synchronize = */ NULL,
};

namespace {
struct ggml_backend_openvino_reg_context {
std::vector<ggml_backend_dev_t> devices;
};
}

static const char * ggml_backend_openvino_reg_get_name(ggml_backend_reg_t reg) {
return GGML_OPENVINO_NAME;
Expand Down
Loading
Loading