[Bugfix] [AITER] [ROCm] Fix Quark MoE Quant Config and AITER Fused MoE quant type logic (#27029)

Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
This commit is contained in:
vllmellm
2025-10-17 12:51:10 -06:00
committed by GitHub
parent b10c64c834
commit e33ee23ee3
3 changed files with 14 additions and 3 deletions
@@ -342,7 +342,8 @@ class QuarkW8A8Fp8MoEMethod(QuarkMoEMethod):
w2_scale=layer.w2_weight_scale,
a1_scale=layer.w13_input_scale,
a2_scale=layer.w2_input_scale,
per_act_token_quant=self.weight_qscheme == "per_channel",
per_act_token_quant=self.input_qscheme == "per_channel",
per_out_ch_quant=self.weight_qscheme == "per_channel",
)
def apply(