(sglang-dev) ubuntu@g-worker-102:~/kebe/sglang$ PYTHONPATH=python python python/sglang/launch_server.py --model ../DeepSeek-R1-Distill-Qwen-32B/ --trust-remote-code  --served-model-name ds --tensor-parallel-size 4 --dtype bfloat16 --max-running-requests 100  --enable-memory-saver
INFO 04-02 13:31:02 __init__.py:190] Automatically detected platform cuda.
enable_memory_saver is enabled, but torch-memory-saver is not installed. Please install it via `pip3 uninstall torch-memory-saver`.
[2025-04-02 13:31:04] server_args=ServerArgs(model_path='../DeepSeek-R1-Distill-Qwen-32B/', tokenizer_path='../DeepSeek-R1-Distill-Qwen-32B/', tokenizer_mode='auto', skip_tokenizer_init=False, load_format='auto', trust_remote_code=True, dtype='bfloat16', kv_cache_dtype='auto', quantization=None, quantization_param_path=None, context_length=None, device='cuda', served_model_name='ds', chat_template=None, completion_template=None, is_embedding=False, revision=None, host='127.0.0.1', port=30000, mem_fraction_static=0.85, max_running_requests=100, max_total_tokens=None, chunked_prefill_size=2048, max_prefill_tokens=16384, schedule_policy='fcfs', schedule_conservativeness=1.0, cpu_offload_gb=0, page_size=1, tp_size=4, stream_interval=1, stream_output=False, random_seed=792507887, constrained_json_whitespace_pattern=None, watchdog_timeout=300, dist_timeout=None, download_dir=None, base_gpu_id=0, gpu_id_step=1, log_level='info', log_level_http=None, log_requests=False, log_requests_level=0, show_time_cost=False, enable_metrics=False, decode_log_interval=40, api_key=None, file_storage_path='sglang_storage', enable_cache_report=False, reasoning_parser=None, dp_size=1, load_balance_method='round_robin', ep_size=1, dist_init_addr=None, nnodes=1, node_rank=0, json_model_override_args='{}', lora_paths=None, max_loras_per_batch=8, lora_backend='triton', attention_backend='flashinfer', sampling_backend='flashinfer', grammar_backend='xgrammar', speculative_algorithm=None, speculative_draft_model_path=None, speculative_num_steps=None, speculative_eagle_topk=None, speculative_num_draft_tokens=None, speculative_accept_threshold_single=1.0, speculative_accept_threshold_acc=1.0, speculative_token_map=None, enable_double_sparsity=False, ds_channel_config_path=None, ds_heavy_channel_num=32, ds_heavy_token_num=256, ds_heavy_channel_type='qk', ds_sparse_decode_threshold=4096, disable_radix_cache=False, disable_cuda_graph=False, disable_cuda_graph_padding=False, enable_nccl_nvls=False, disable_outlines_disk_cache=False, disable_custom_all_reduce=False, disable_mla=False, disable_overlap_schedule=False, enable_mixed_chunk=False, enable_dp_attention=False, enable_ep_moe=False, enable_deepep_moe=False, deepep_mode=None, enable_torch_compile=False, torch_compile_max_bs=32, cuda_graph_max_bs=80, cuda_graph_bs=None, torchao_config='', enable_nan_detection=False, enable_p2p_check=False, triton_attention_reduce_in_fp32=False, triton_attention_num_kv_splits=8, num_continuous_decode_steps=1, delete_ckpt_after_loading=False, enable_memory_saver=True, allow_auto_truncate=False, enable_custom_logit_processor=False, tool_call_parser=None, enable_hierarchical_cache=False, hicache_ratio=2.0, enable_flashinfer_mla=False, enable_flashmla=False, flashinfer_mla_disable_ragged=False, warmups=None, debug_tensor_dump_output_folder=None, debug_tensor_dump_input_file=None, debug_tensor_dump_inject=False, disaggregation_mode='null', disaggregation_bootstrap_port=8998)
Traceback (most recent call last):
  File "/home/ubuntu/kebe/sglang/python/sglang/launch_server.py", line 14, in <module>
    launch_server(server_args)
  File "/home/ubuntu/kebe/sglang/python/sglang/srt/entrypoints/http_server.py", line 679, in launch_server
    tokenizer_manager, scheduler_info = _launch_subprocesses(server_args=server_args)
  File "/home/ubuntu/kebe/sglang/python/sglang/srt/entrypoints/engine.py", line 494, in _launch_subprocesses
    with memory_saver_adapter.configure_subprocess():
  File "/home/ubuntu/kebe/sglang/python/sglang/srt/torch_memory_saver_adapter.py", line 48, in configure_subprocess
    return torch_memory_saver.configure_subprocess()
NameError: name 'torch_memory_saver' is not defined