vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

llama : cleanup unused mmq flags (#5772)

Browse source 
* cleanup unused --no-mul-mat-q,-nommq, -mmq, --mul-mat-q, mul_mat_q

* remove: mul_mat_q in compare llama bench and usage

* update llama-bench

---------

Co-authored-by: slaren <slarengh@gmail.com>
This commit is contained in:
Pierrick Hymbert 2024-03-01 12:39:06 +01:00 • committed by GitHub
parent 9600d59e01
commit 3ab8b3a92e
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
9 changed files with 10 additions and 56 deletions
Download patch file Download diff file Expand all files Collapse all files

8
examples/server/server.cpp
View file

@ -2390,14 +2390,6 @@ static void server_params_parse(int argc, char **argv, server_params &sparams,
}
#else
LOG_WARNING("llama.cpp was compiled without cuBLAS. It is not possible to set a tensor split.\n", {});
#endif // GGML_USE_CUBLAS
}
else if (arg == "--no-mul-mat-q" || arg == "-nommq")
{
#if defined(GGML_USE_CUBLAS) || defined(GGML_USE_SYCL)
params.mul_mat_q = false;
#else
LOG_WARNING("warning: llama.cpp was compiled without cuBLAS. Disabling mul_mat_q kernels has no effect.\n", {});
#endif // GGML_USE_CUBLAS
}
else if (arg == "--main-gpu" || arg == "-mg")