wylab/llama.cpp
1
0
Fork 1
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-06-09 07:16:44 +02:00
Code Issues Packages Projects Releases Wiki Activity

hexagon: profiler output fix and script updates (#24042)

Browse Source 
* hex-ops: fix profiler output (ie remove the redundant NONEs)

* hex-prof: update profiling script to support tot.usec column
This commit is contained in:
Max Krasnyansky
2026-06-02 14:08:29 -07:00
committed by GitHub
parent 4fb16eccce
commit 5c394fdc8b
2 changed files with 31 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-hexagon/htp-opnode.h
+17 -10
View File
@@ -56,6 +56,20 @@ struct htp_opnode {
}
std::vector<const ggml_tensor *> get_inputs() const {
if (fused.empty()) {
int last_non_null = -1;
for (int i = 0; i < GGML_MAX_SRC; i++) {
if (node->src[i]) {
last_non_null = i;
}
}
std::vector<const ggml_tensor *> inputs(last_non_null + 1, nullptr);
for (int i = 0; i <= last_non_null; i++) {
inputs[i] = node->src[i];
}
return inputs;
}
std::vector<const ggml_tensor *> inputs(GGML_MAX_SRC, nullptr);
std::vector<const ggml_tensor *> outputs;
outputs.push_back(node);
@@ -82,12 +96,8 @@ struct htp_opnode {
};
for (int i = 0; i < GGML_MAX_SRC; i++) {
if (fused.empty()) {
inputs[i] = node->src[i];
} else {
if (node->src[i]) {
add_input(node->src[i]);
}
if (node->src[i]) {
add_input(node->src[i]);
}
}
for (const auto * f : fused) {
@@ -98,10 +108,7 @@ struct htp_opnode {
}
}
if (!fused.empty()) {
inputs.resize(count);
}
inputs.resize(count);
return inputs;
}