增加w8a8相关修改

vllm/model_executor/models/falcon.py

@@ -462,7 +462,7 @@ class FalconForCausalLM(nn.Module, SupportsPP):
         self.use_gemm_pad = os.environ.get('GEMM_PAD') == '1'
         self.use_fa_pad = os.environ.get('FA_PAD') == '1'
         self.use_awq_pad = os.environ.get('AWQ_PAD') == '1'
-        self.w8a8_strategy=int(os.getenv('W8A8_SUPPORT_METHODS', '0'))
+        self.w8a8_strategy=int(os.getenv('W8A8_SUPPORT_METHODS', '1'))
 
     def get_input_embeddings(self, input_ids: torch.Tensor) -> torch.Tensor:
         return self.transformer.get_input_embeddings(input_ids)