A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 14, 05:30 UTC
[BUGFIX] KeyError 'layers.14.mlp.gate.g_idx' for Qwen3-MoE with GPTQ on ROCm (#22017)
JartX committed
Aug 11, 2025 at 09:13 UTC
1e55dfa7e552e0995630a2563aeae443945e2e81
1 file changed
+1
-1
vllm/model_executor/models/qwen3_moe.py
+1
-1
@@ -149,7 +149,7 @@ class Qwen3MoeSparseMoeBlock(nn.Module):
149
self.gate = ReplicatedLinear(config.hidden_size,
150
config.num_experts,
151
bias=False,
152
- quant_config=None,
152
+ quant_config=quant_config,
153
prefix=f"{prefix}.gate")
154
155
def forward(self, hidden_states: torch.Tensor) -> torch.Tensor: