vrr/prima.cpp
2
0
Fork 0
mirror of https://github.com/Lizonghang/prima.cpp.git synced 2025-09-06 15:59:07 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

do not check loaded tensors due to increased latency

Browse source
This commit is contained in:
Lizonghang 2025-02-11 17:10:11 +04:00
parent 3dd3138207
commit 65ad14140a
1 changed files with 0 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
src/llama.cpp
View file

@ -17794,8 +17794,6 @@ static void manage_graph_tensors(struct ggml_cgraph * cgraph, int advice, bool f
if (lower_name.find("cuda") != std::string::npos) continue;
}
if (is_tensor_loaded(cur)) continue;
size_t size = ggml_nbytes(cur);
size_t first = reinterpret_cast<size_t>(cur->data);
size_t last = first + size;