thek0tyara/llama-cpp-turboquant
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 4

llama-bench: print -n-cpu-moe when offloaded layers > 1 (#20984)

Browse source
This commit is contained in:
Aman Gupta 2026-03-25 21:17:27 +08:00 • committed by GitHub
parent b2704f9028
commit 9c600bcd4b
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
tools/llama-bench/llama-bench.cpp
View file

@ -1807,7 +1807,7 @@ struct markdown_printer : public printer {
if (!is_cpu_backend) {
fields.emplace_back("n_gpu_layers");
}
if (params.n_cpu_moe.size() > 1) {
if (params.n_cpu_moe.size() > 1 || params.n_cpu_moe != cmd_params_defaults.n_cpu_moe) {
fields.emplace_back("n_cpu_moe");
}
if (params.n_threads.size() > 1 || params.n_threads != cmd_params_defaults.n_threads || is_cpu_backend) {