Skip to content

Added performance analysis as a feature with AutoModelForCausalLM #888

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

Open
ochougul wants to merge 3 commits into
base: main
Choose a base branch
from
+805 −1
Open

Added performance analysis as a feature with AutoModelForCausalLM #888

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
a47b6e6
added way to get performance stats automtically in qeff AutoModelForC…
ochougul Mar 25, 2026
160b819
removed redundancies
ochougul Mar 25, 2026
aec6eae
added prefill-only flag and prefill/decode run by default
ochougul Mar 25, 2026
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
6 changes: 6 additions & 0 deletions QEfficient/base/modeling_qeff.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -390,6 +390,12 @@ def _compile(

For QNN Compilation path, when enable_qnn is set to True, any parameter passed in compiler_options will be ignored.
"""
# Backward-compatible alias accepted by some APIs.
if "aic_perf_warning" in compiler_options:
if "aic_perf_warnings" not in compiler_options:
compiler_options["aic_perf_warnings"] = compiler_options["aic_perf_warning"]
compiler_options.pop("aic_perf_warning", None)

onnx_path = Path(
onnx_path
if onnx_path
Expand Down
Loading
Loading