Revert "Optimized deepseek-v3/r1 model performance on mxfp4 run (#9671)" (#9959)

This commit is contained in:
Yineng Zhang
2025-09-03 00:50:04 -07:00
committed by GitHub
parent 2c7ca33abb
commit 1b2ff4fb7f
7 changed files with 59 additions and 455 deletions
@@ -1,13 +0,0 @@
from aiter.ops.triton.batched_gemm_afp4wfp4_pre_quant import (
batched_gemm_afp4wfp4_pre_quant,
)
from aiter.ops.triton.fused_mxfp4_quant import (
fused_flatten_mxfp4_quant,
fused_rms_mxfp4_quant,
)
__all__ = [
"fused_rms_mxfp4_quant",
"fused_flatten_mxfp4_quant",
"batched_gemm_afp4wfp4_pre_quant",
]