[Bugfix] Fix ColumnParallelLinearWithLoRA slice (vllm-project#11708)

Signed-off-by: ZincCat <[email protected]>

Author: zinccat

vllm/lora/layers.py

@@ -479,7 +479,7 @@ def slice_lora_b(self, lora_b: torch.Tensor) -> torch.Tensor:
         # ColumnParallelLinear.
         else:
             tensor_model_parallel_rank = get_tensor_model_parallel_rank()
-            shard_size = self.output_dim
+            shard_size = self.output_size
             start_idx = tensor_model_parallel_rank * shard_size
             end_idx = (tensor_model_parallel_rank + 1) * shard_size
             lora_b = lora_b[:, start_idx:end_idx]
@@ -490,7 +490,7 @@ def slice_bias(self, bias: torch.Tensor) -> torch.Tensor:
         if bias is None:
             return bias
         tensor_model_parallel_rank = get_tensor_model_parallel_rank()
-        shard_size = self.output_dim
+        shard_size = self.output_size
         start_idx = tensor_model_parallel_rank * shard_size
         end_idx = (tensor_model_parallel_rank + 1) * shard_size
         bias = bias[start_idx:end_idx]