zhangyiss/mlx-examples
1
0
Fork 0
mirror of https://github.com/ml-explore/mlx-examples.git synced 2025-08-30 02:53:41 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

format

Browse Source
This commit is contained in:
Awni Hannun 2024-10-21 14:03:15 -07:00
parent 645423946a
commit 3263d17ea0
1 changed files with 6 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
llms/mlx_lm/generate.py
View File

@ -111,8 +111,10 @@ def setup_arg_parser():
"--wire-model", "--wire-model",
"-w", "-w",
action="store_true", action="store_true",
help=("Keep the model resident in memory. This can substantially " help=(
"speedup generation for models large relative to the machine's RAM.") "Keep the model resident in memory. This can substantially "
"speedup generation for models large relative to the machine's RAM."
),
) )
return parser return parser
@ -230,7 +232,8 @@ def main():
raise ValueError( raise ValueError(
"Cannot wire a model larger than the available RAM. You may " "Cannot wire a model larger than the available RAM. You may "
"be able to increase the available RAM by setting " "be able to increase the available RAM by setting "
"`sudo sysctl iogpu.wired_limit_mb=N` to a larger value") "`sudo sysctl iogpu.wired_limit_mb=N` to a larger value"
)
response = generate( response = generate(
model, model,