nikola/llama_cpp
1
0
Fork 0
Code Issues Pull Requests Actions 4 Packages Projects Releases Wiki Activity

bench : add --offline (#24511)

Browse Source 
* bench : add --offline

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

* Add default

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

---------

Signed-off-by: Adrien Gallouët <angt@huggingface.co>
This commit is contained in:
Adrien Gallouët
2026-06-16 08:26:05 +02:00
committed by GitHub
parent ac79caa7ce
commit e3a74b2990
2 changed files with 10 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
tools/server/bench/bench.py
View File

@@ -40,6 +40,7 @@ def main(args_in: list[str] | None = None) -> None:
required=True)
parser.add_argument("--hf-repo", type=str, help="Hugging Face model repository", required=True)
parser.add_argument("--hf-file", type=str, help="Hugging Face model file", required=True)
parser.add_argument("--offline", action="store_true", default=False, help="Offline mode: forces use of cache, prevents network access")
parser.add_argument("-ngl", "--n-gpu-layers", type=int, help="layers to the GPU for computation", required=True)
parser.add_argument("--ctx-size", type=int, help="Set the size of the prompt context", required=True)
parser.add_argument("--parallel", type=int, help="Set the number of slots for process requests", required=True)
@@ -268,6 +269,8 @@ def start_server_background(args):
]
server_args.extend(['--hf-repo', args.hf_repo])
server_args.extend(['--hf-file', args.hf_file])
if args.offline:
server_args.append('--offline')
server_args.extend(['--n-gpu-layers', args.n_gpu_layers])
server_args.extend(['--ctx-size', args.ctx_size])
server_args.extend(['--parallel', args.parallel])