[MoE] Plumb gemm1_alpha/beta/clamp_limit into TRT-LLM FP8 MoE (#45723)
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com> Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
co-authored by
Claude Opus 4.8
parent
d3229431f9
commit
fa248139a0
@@ -224,6 +224,8 @@ class Mxfp8OnlineMoEMethod(OnlineMoEMethodBase):
|
||||
w2_bias=getattr(layer, "w2_bias", None),
|
||||
block_shape=self.weight_block_size,
|
||||
swiglu_limit=getattr(layer, "swiglu_limit", None),
|
||||
gemm1_alpha=getattr(layer, "swiglu_alpha", None),
|
||||
gemm1_beta=getattr(layer, "swiglu_beta", None),
|
||||
)
|
||||
|
||||
def process_weights_after_loading(self, layer: Module) -> None:
|
||||
|
||||
Reference in New Issue
Block a user