Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

add param in profile_mlp.py to enable graph mode or not #106

Merged
merged 2 commits into from
Jul 25, 2024
Merged

add param in profile_mlp.py to enable graph mode or not #106

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
cd29e82
add param in profile_mlp.py to enable graph mode or not
xduzhangjiayu Jul 24, 2024
544d339
Merge branch 'main' into add_param_profile_mlp
alessandropalla Jul 25, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 9 additions & 1 deletion script/profile_mlp.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,6 +20,7 @@ def main(
intermediate_size=512,
dtype="float16",
_profile=False,
enable_graph_mode=False,
):

conf = Phi3Config.from_pretrained("microsoft/Phi-3-mini-4k-instruct")
Expand All @@ -44,7 +45,7 @@ def main(
raise RuntimeError(f"Invalid dtype: {dtype}")

# Compile model
compiler_conf = CompilerConfig(use_to=True, dtype=dtype)
compiler_conf = CompilerConfig(use_to=enable_graph_mode, dtype=dtype)
model = intel_npu_acceleration_library.compile(mlp, compiler_conf)
if _profile:
model.profile = True
Expand Down Expand Up @@ -106,6 +107,12 @@ def define_and_parse_args():
default=False,
help="Enable the profiling (default: False)",
)
parser.add_argument(
"--enable_graph_mode",
action="store_true",
default=False,
help="Enable graph mode for MLP, otherwise use eager mode (default: False)",
)

return parser.parse_args()

Expand All @@ -123,4 +130,5 @@ def define_and_parse_args():
intermediate_size=args.intermediate_size,
dtype=args.dtype,
_profile=args.profile,
enable_graph_mode=args.enable_graph_mode,
)
Loading