Unverified Commit 1e55dfa7 authored by JartX's avatar JartX Committed by GitHub
Browse files

[BUGFIX] KeyError 'layers.14.mlp.gate.g_idx' for Qwen3-MoE with GPTQ on ROCm (#22017)

parent 384a0529
...@@ -149,7 +149,7 @@ class Qwen3MoeSparseMoeBlock(nn.Module): ...@@ -149,7 +149,7 @@ class Qwen3MoeSparseMoeBlock(nn.Module):
self.gate = ReplicatedLinear(config.hidden_size, self.gate = ReplicatedLinear(config.hidden_size,
config.num_experts, config.num_experts,
bias=False, bias=False,
quant_config=None, quant_config=quant_config,
prefix=f"{prefix}.gate") prefix=f"{prefix}.gate")
def forward(self, hidden_states: torch.Tensor) -> torch.Tensor: def forward(self, hidden_states: torch.Tensor) -> torch.Tensor:
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment