Skip to content

[hotfix] always use fp4x2 for swiglu separated per_1x32 path #3591

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
yadaish wants to merge 1 commit into
base: main
Choose a base branch
from
+1 −1
Open

[hotfix] always use fp4x2 for swiglu separated per_1x32 path #3591

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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 aiter/fused_moe.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -402,7 +402,7 @@ def fused_moe_(
q_dtype_a = dtypes.bf16
elif quant_type == QuantType.per_1x32:
if activation == ActivationType.Swiglu and gate_mode == GateMode.SEPARATED:
q_dtype_a = dtypes.bf16 if M < _SWIGLU_MXFP4_BF16_BOUND else dtypes.fp4x2
q_dtype_a = dtypes.fp4x2
elif activation == ActivationType.Swiglu or gate_mode == GateMode.INTERLEAVE:
if get_gfx() != "gfx950" or M < bf16_fp8_bound:
q_dtype_a = dtypes.bf16
Expand Down
Loading