[ROCm][Quant] Minimax-M3: Enable fp8_per_channel for bf16 weights on mi300x (#45854)

Signed-off-by: Hongxia Yang <hongxia.yang@amd.com>
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
Co-authored-by: tjtanaa <tunjian.tan@embeddedllm.com>
This commit is contained in:
Hongxia Yang
2026-06-17 12:02:40 +00:00
committed by GitHub
co-authored by tjtanaa
parent ee0fd6984a
commit e28e8c8782
5 changed files with 11 additions and 0 deletions
@@ -603,6 +603,8 @@ def fp8_w8a8_moe_quant_config(
a2_gscale: torch.Tensor | None = None,
g1_alphas: torch.Tensor | None = None,
g2_alphas: torch.Tensor | None = None,
gemm1_alpha: float | None = None,
gemm1_beta: float | None = None,
gemm1_clamp_limit: float | None = None,
) -> FusedMoEQuantConfig:
"""
@@ -623,6 +625,8 @@ def fp8_w8a8_moe_quant_config(
per_act_token_quant=per_act_token_quant,
per_out_ch_quant=per_out_ch_quant,
block_shape=block_shape,
gemm1_alpha=gemm1_alpha,
gemm1_beta=gemm1_beta,
gemm1_clamp_limit=gemm1_clamp_limit,
)