Using a more precise profiling on ROCm to properly account for weight…

…s padding (#394)

Signed-off-by: Gregory Shtrasberg <[email protected]>

vllm/platforms/rocm.py

@@ -164,4 +164,4 @@ def get_current_memory_usage(cls,
                                  device: Optional[torch.types.Device] = None
                                  ) -> float:
         torch.cuda.reset_peak_memory_stats(device)
-        return torch.cuda.max_memory_allocated(device)
+        return torch.cuda.mem_get_info()[1] - torch.cuda.mem_get_info()[0]