common: fix missing exports in llama-common (#22340)

* common: refactor common/debug to move abort_on_nan into base_callback_data

Passing bool abort_on_nan as template parameter for common_debug_cb_eval is unnecessary and creates an issue with LTO.
It should just be a member of the base_callback_data instead.

* cont : cleanup

* common : use pimpl in debug.h to reduce header dependencies

Move common_debug_cb_user_data's data members (std::regex,
std::vector<uint8_t>) into a private impl struct in debug.cpp.

This removes the includes of common.h and <regex> from debug.h,
reducing transitive dependencies for any translation unit that
includes the header.

Assisted-by: llama.cpp:local pi

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
Max Krasnyansky
2026-04-26 22:06:39 -07:00
committed by GitHub
parent f535774325
commit 5594d13224
6 changed files with 72 additions and 58 deletions
+40 -17
View File
@@ -1,9 +1,38 @@
#include "debug.h"
#include "common.h"
#include "log.h"
#include <cmath>
#include <regex>
#include <string>
#include <vector>
struct common_debug_cb_user_data::impl {
std::vector<uint8_t> data;
std::vector<std::regex> tensor_filters;
bool abort_on_nan{false};
};
common_debug_cb_user_data::common_debug_cb_user_data() : pimpl(std::make_unique<impl>()) {}
common_debug_cb_user_data::~common_debug_cb_user_data() = default;
common_debug_cb_user_data::common_debug_cb_user_data(common_params & params, const std::vector<std::string> & filter_patterns, bool abort_on_nan)
: pimpl(std::make_unique<impl>())
{
for (const auto & pattern : filter_patterns) {
try {
std::string anchored_pattern = "^" + pattern;
pimpl->tensor_filters.emplace_back(anchored_pattern, std::regex::optimize);
} catch (const std::regex_error & e) {
throw std::runtime_error("Invalid regex pattern '" + pattern + "': " + e.what());
}
}
pimpl->abort_on_nan = abort_on_nan;
params.cb_eval = common_debug_cb_eval;
params.cb_eval_user_data = this;
}
static std::string common_ggml_ne_string(const ggml_tensor * t) {
std::string str;
@@ -47,8 +76,7 @@ static float common_ggml_get_float_value(const uint8_t * data,
#define INDENT " "
template <bool abort>
void common_debug_print_tensor(uint8_t * data, ggml_type type, const int64_t * ne, const size_t * nb, int64_t n) {
static void common_debug_print_tensor(uint8_t * data, ggml_type type, const int64_t * ne, const size_t * nb, int64_t n, bool abort_on_nan) {
GGML_ASSERT(n > 0);
float sum = 0;
for (int64_t i3 = 0; i3 < ne[3]; i3++) {
@@ -94,7 +122,7 @@ void common_debug_print_tensor(uint8_t * data, ggml_type type, const int64_t * n
LOG(INDENT "sum = %f\n", sum);
}
if constexpr (abort) {
if (abort_on_nan) {
if (std::isnan(sum)) {
LOG("encountered NaN - aborting\n");
exit(0);
@@ -112,8 +140,9 @@ void common_debug_print_tensor(uint8_t * data, ggml_type type, const int64_t * n
* @param user_data user data to pass at each call back
* @return true to receive data or continue the graph, false otherwise
*/
template <bool abort_on_nan> bool common_debug_cb_eval(struct ggml_tensor * t, bool ask, void * user_data) {
auto * cb_data = (base_callback_data *) user_data;
bool common_debug_cb_eval(struct ggml_tensor * t, bool ask, void * user_data) {
auto * cb_data = (common_debug_cb_user_data *) user_data;
auto * pimpl = cb_data->pimpl.get();
const struct ggml_tensor * src0 = t->src[0];
const struct ggml_tensor * src1 = t->src[1];
@@ -122,10 +151,10 @@ template <bool abort_on_nan> bool common_debug_cb_eval(struct ggml_tensor * t, b
return true; // Always retrieve data
}
bool matches_filter = cb_data->tensor_filters.empty();
bool matches_filter = pimpl->tensor_filters.empty();
if (!matches_filter) {
for (const auto & filter : cb_data->tensor_filters) {
for (const auto & filter : pimpl->tensor_filters) {
if (std::regex_search(t->name, filter)) {
matches_filter = true;
break;
@@ -148,20 +177,14 @@ template <bool abort_on_nan> bool common_debug_cb_eval(struct ggml_tensor * t, b
if (!is_host) {
auto n_bytes = ggml_nbytes(t);
cb_data->data.resize(n_bytes);
ggml_backend_tensor_get(t, cb_data->data.data(), 0, n_bytes);
pimpl->data.resize(n_bytes);
ggml_backend_tensor_get(t, pimpl->data.data(), 0, n_bytes);
}
if (!ggml_is_quantized(t->type) && matches_filter) {
uint8_t * data = is_host ? (uint8_t *) t->data : cb_data->data.data();
common_debug_print_tensor<abort_on_nan>(data, t->type, t->ne, t->nb, 3);
uint8_t * data = is_host ? (uint8_t *) t->data : pimpl->data.data();
common_debug_print_tensor(data, t->type, t->ne, t->nb, 3, pimpl->abort_on_nan);
}
return true;
}
// Explicit template instantiations
template bool common_debug_cb_eval<false>(ggml_tensor *, bool, void *);
template bool common_debug_cb_eval<true>(ggml_tensor *, bool, void *);
template void common_debug_print_tensor<false>(uint8_t *, ggml_type, const int64_t *, const size_t *, int64_t);
template void common_debug_print_tensor<true>(uint8_t *, ggml_type, const int64_t *, const size_t *, int64_t);
+17 -29
View File
@@ -1,43 +1,31 @@
#pragma once
#include "common.h"
#include <memory>
#include <string>
#include <vector>
#include <regex>
// common debug functions and structs
// Print a tensor's detailed data
// data - the tensor's data in byte format
// type - the tensor's quantization type
// ne - the tensor dimensions array
// nb - the tensor strides array
// n - the number of rows/columns to fully print
template <bool abort_on_nan> void common_debug_print_tensor(uint8_t * data, ggml_type type, const int64_t * ne, const size_t * nb, int64_t n);
struct common_params;
// Intended to use as callback for ggml_backend_sched_eval_callback
// prints tensors that are processed in the computation graph
// by default prints all tensors, but can be configured by creating a `base_callback_data` instance with
// non-empty filter_patterns. See examples/debug.ccp for possible usage patterns
// The template parameter determines whether an error should be thrown whenever a NaN is encountered
// by default prints all tensors, but can be configured by creating a `common_debug_cb_user_data` instance with
// non-empty filter_patterns. See examples/debug.cpp for possible usage patterns
// `common_debug_cb_user_data` contains `abort_on_nan` flag that determines whether an error should be thrown whenever a NaN is encountered
// in a tensor (useful for stopping debug sessions on first erroneous tensor)
// The callback data will be passed as the third parameter (user_data)
template <bool abort_on_nan> bool common_debug_cb_eval(struct ggml_tensor * t, bool ask, void * user_data);
struct base_callback_data {
std::vector<uint8_t> data;
std::vector<std::regex> tensor_filters;
bool common_debug_cb_eval(struct ggml_tensor * t, bool ask, void * user_data);
base_callback_data() = default;
struct common_debug_cb_user_data {
struct impl;
std::unique_ptr<impl> pimpl;
base_callback_data(common_params & params, const std::vector<std::string> & filter_patterns) {
for (const auto & pattern : filter_patterns) {
try {
std::string anchored_pattern = "^" + pattern;
tensor_filters.emplace_back(anchored_pattern, std::regex::optimize);
} catch (const std::regex_error & e) {
throw std::runtime_error("Invalid regex pattern '" + pattern + "': " + e.what());
}
}
params.cb_eval = common_debug_cb_eval<false>;
params.cb_eval_user_data = this;
}
common_debug_cb_user_data();
~common_debug_cb_user_data();
common_debug_cb_user_data(const common_debug_cb_user_data &) = delete;
common_debug_cb_user_data & operator=(const common_debug_cb_user_data &) = delete;
common_debug_cb_user_data(common_params & params, const std::vector<std::string> & filter_patterns, bool abort_on_nan = false);
};