Skip to content

tests: xfail moe quantization classes mxfp8_bf16 UTs on sm103 #1754

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

Merged
yzh119 merged 2 commits into from
Sep 22, 2025
Merged

tests: xfail moe quantization classes mxfp8_bf16 UTs on sm103 #1754

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
1a6d14e
xfail mxfp8bf16 on sm103
jimmyzho Sep 19, 2025
5014727
comment
jimmyzho Sep 22, 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
11 changes: 11 additions & 0 deletions tests/test_trtllm_gen_fused_moe.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2034,6 +2034,17 @@ def test_moe_quantization_classes(
f"Incompatible: {moe_impl.name} + {weight_processing['use_shuffled_weight']} + {weight_processing['layout']}"
)

# TODO(jimmzhou): enable MxFP4xBf16 on SM103
if (
type(moe_impl) is FP4Moe
and moe_impl.quant_mode == QuantMode.FP4_MXFP4_Bf16
and compute_capability[0] == 10
and compute_capability[1] == 3
):
Comment on lines +2038 to +2043

@gemini-code-assist gemini-code-assist Bot Sep 22, 2025

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

For better code style and robustness, it's recommended to use isinstance() for type checking instead of type() is. isinstance() correctly handles inheritance. Additionally, comparing the compute_capability tuple directly with (10, 3) is more concise and readable.

    if (
        isinstance(moe_impl, FP4Moe)
        and moe_impl.quant_mode == QuantMode.FP4_MXFP4_Bf16
        and compute_capability == (10, 3)
    ):

pytest.xfail(
"Note(jimmzhou): Make MxFP4xBf16 nonfunctional on SM103 to avoid B200 regression"
)

moe_impl._cache_permute_indices = cache_permute_indices

seed = 0
Expand Down