Skip to content

[ExecuTorch][llm] Add source-transform and Meta-kernel tests for MoE op #21122

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
digantdesai wants to merge 3 commits into
base: gh/digantdesai/72/base
Choose a base branch
from
+545 −0
Open

[ExecuTorch][llm] Add source-transform and Meta-kernel tests for MoE op #21122

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
45e1787
Update
digantdesai Jul 22, 2026
6f7bf13
Update
digantdesai Jul 22, 2026
13289b9
Update
digantdesai Jul 23, 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
3 changes: 3 additions & 0 deletions .ci/scripts/test_llama_torchao_lowbit.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -50,6 +50,9 @@ cmake -DPYTHON_EXECUTABLE=python \
examples/models/llama
cmake --build cmake-out/examples/models/llama -j16 --config Release

${PYTHON_EXECUTABLE} -m pytest \
extension/llm/custom_ops/test_quantized_moe.py

# Download stories llama110m artifacts
download_stories_model_artifacts

Expand Down
19 changes: 19 additions & 0 deletions extension/llm/custom_ops/BUCK
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -102,3 +102,22 @@ fbcode_target(_kind = runtime.python_binary,
],
deps = ["//caffe2:torch"],
)

fbcode_target(_kind = runtime.python_test,
name = "test_quantized_moe",
srcs = [
"test_quantized_moe.py",
],
preload_deps = [
":custom_ops_aot_lib_mkl_noomp",
":custom_ops_aot_py",
"//pytorch/ao/torchao/csrc/cpu/shared_kernels/linear_8bit_act_xbit_weight:op_linear_8bit_act_xbit_weight_aten",
],
deps = [
"//caffe2:torch",
"//executorch/extension/pybindings:portable_lib",
"//executorch/examples/models/llama:llama_transformer",
"//executorch/examples/models/llama:transformer_modules",
"//executorch/examples/models/llama:source_transformation",
],
)
Loading
Loading