Fix GGUF loader for Qwen3 MoE. (#22785)

Signed-off-by: Gh0u1L5 <Gh0u1L5@outlook.com>
2025-08-13 21:08:23 +08:00
parent 6772bb0f7d
commit b159c0a67a
2 changed files with 12 additions and 0 deletions
--- a/vllm/model_executor/models/qwen3_moe.py
+++ b/vllm/model_executor/models/qwen3_moe.py
@@ -375,6 +375,7 @@ class Qwen3MoeModel(nn.Module):
        self.embed_tokens = VocabParallelEmbedding(
            config.vocab_size,
            config.hidden_size,
+            quant_config=quant_config,
            prefix=f"{prefix}.embed_tokens")
        self.start_layer, self.end_layer, self.layers = make_layers(
            config.num_hidden_layers,