xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-05-30 04:37:04 +08:00
Code Issues Packages Projects Releases Wiki Activity

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

Browse Source
This commit is contained in:
JartX 2025-08-11 09:13:30 +02:00 committed by GitHub
parent 384a052971
commit 1e55dfa7e5
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/model_executor/models/qwen3_moe.py
View File

@ -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: