pingu_98/llama_cpp_for_radxa_dragon_wing_q6a
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Fix type casting for unaccounted memory calculation (#22424)

Browse source
This commit is contained in:
rankaiyx 2026-04-27 20:31:13 +08:00 committed by GitHub
parent e940b3d468
commit 42401c72b8
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 2 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
common/fit.cpp
View file

@ -856,7 +856,7 @@ void common_memory_breakdown_print(const struct llama_context * ctx) {
ggml_backend_dev_memory(dev, &free, &total);
const size_t self = mb.model + mb.context + mb.compute;
const size_t unaccounted = total - self - free;
const int64_t unaccounted = static_cast<int64_t>(total) - static_cast<int64_t>(free) - static_cast<int64_t>(self);
table_data.push_back({
template_gpu,
@ -867,7 +867,7 @@ void common_memory_breakdown_print(const struct llama_context * ctx) {
std::to_string(mb.model / MiB),
std::to_string(mb.context / MiB),
std::to_string(mb.compute / MiB),
std::to_string(unaccounted / MiB)});
std::to_string(unaccounted / static_cast<int64_t>(MiB))});
}
// print memory breakdown for host: