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

YAML result logging + preset script (#2657)

Browse source
This commit is contained in:
Johannes Gäßler 2023-08-28 17:59:39 +02:00 • committed by GitHub
parent 75fafcbccc
commit 6b73ef1201
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
8 changed files with 700 additions and 42 deletions
Download patch file Download diff file Expand all files Collapse all files

2
examples/server/server.cpp
View file

@ -719,7 +719,7 @@ static void server_print_usage(const char *argv0, const gpt_params &params,
fprintf(stdout, " -ts SPLIT --tensor-split SPLIT\n");
fprintf(stdout, " how to split tensors across multiple GPUs, comma-separated list of proportions, e.g. 3,1\n");
fprintf(stdout, " -mg i, --main-gpu i the GPU to use for scratch and small tensors\n");
fprintf(stdout, " -lv, --low-vram don't allocate VRAM scratch buffer\n");
fprintf(stdout, " -lv, --low-vram don't allocate VRAM scratch buffer\n");
fprintf(stdout, " -nommq, --no-mul-mat-q\n");
fprintf(stdout, " use cuBLAS instead of custom mul_mat_q CUDA kernels.\n");
fprintf(stdout, " Not recommended since this is both slower and uses more VRAM.\n");