Merge branch 'v0.9.2-dev' into 'v0.9.2-dev-add_connector'

# Conflicts:
#   vllm/distributed/kv_transfer/kv_connector/v1/p2p/p2p_nccl_engine.py

vllm/model_executor/models/falcon.py

@@ -58,6 +58,7 @@ from .utils import (AutoWeightsLoader, is_pp_missing_parameter,
 
 from vllm import _custom_ops as ops
 from vllm.model_executor.utils import pad_weight, gemm_bank_conf
+import vllm.envs as envs
 
 FalconConfig = Union[HF_FalconConfig, RWConfig]
 
@@ -393,7 +394,7 @@ class FalconModel(nn.Module):
         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', '1'))
+        self.w8a8_strategy = envs.VLLM_W8A8_BACKEND
 
     def get_input_embeddings(self, input_ids: torch.Tensor) -> torch.Tensor:
         return self.word_embeddings(input_ids)