[BUGFIX][Qwen3.5] Hardcode mlp.gate as not quantizable (#35156)

Signed-off-by: Vadim Gimpelson <vadim.gimpelson@gmail.com>
This commit is contained in:
Vadim Gimpelson
2026-02-24 07:42:24 +04:00
committed by GitHub
parent 80d93fd6da
commit 33a0d43c71

View File

@@ -252,7 +252,7 @@ class Qwen3NextSparseMoeBlock(nn.Module):
config.hidden_size,
config.num_experts,
bias=False,
quant_config=quant_config,
quant_config=None,
prefix=f"{prefix}.gate",
)