Revert "Add simple CPU offloading support" (#2252)

We'll re-add the commit to correctly ack Kaichao's authorship

python/sglang/srt/model_executor/model_runner.py

@@ -61,7 +61,6 @@ from sglang.srt.utils import (
     is_hip,
     monkey_patch_vllm_model_config,
     monkey_patch_vllm_p2p_access_check,
-    set_cpu_offload_max_bytes,
 )
 
 logger = logging.getLogger(__name__)
@@ -146,8 +145,6 @@ class ModelRunner:
             }
         )
 
-        set_cpu_offload_max_bytes(int(server_args.cpu_offload_gb * 1024**3))
-
         # Init components
         min_per_gpu_memory = self.init_torch_distributed()
         self.sampler = Sampler()