Skip to content

[Test] int8wo run in CI #3347

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

Draft
wants to merge 2 commits into
base: main
Choose a base branch
from
+6 −6
Draft

[Test] int8wo run in CI #3347

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
2de61f6
Test int8wo delay
jainapurva Nov 17, 2025
588019e
Update quantization config for small_bf16_linear model
jainapurva Nov 17, 2025
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
2 changes: 1 addition & 1 deletion .github/workflows/run_microbenchmarks.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,7 +22,7 @@ jobs:
- name: Setup miniconda
uses: pytorch/test-infra/.github/actions/setup-miniconda@main
with:
python-version: "3.9"
python-version: "3.10"

- name: Run benchmark
shell: bash
Expand Down
10 changes: 5 additions & 5 deletions benchmarks/dashboard/microbenchmark_quantization_config.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,17 +2,17 @@
benchmark_mode: "inference"
quantization_config_recipe_names: # Will run a baseline inference for model by default, without quantization for comparison
- "int8wo"
- "int8dq"
- "float8dq-tensor"
- "float8dq-row"
- "float8wo"
# - "int8dq"
# - "float8dq-tensor"
# - "float8dq-row"
# - "float8wo"
output_dir: "benchmarks/microbenchmarks/results"
model_params:
- name: "small_bf16_linear"
matrix_shapes:
- name: "small_sweep"
min_power: 10
max_power: 15
max_power: 14
high_precision_dtype: "torch.bfloat16"
torch_compile_mode: "max-autotune"
device: "cuda"
Expand Down