runtime error

Exit code: 1. Reason: .9/site-packages/vllm/worker/cpu_worker.py", line 259, in initialize_cache self._validate_num_cpu_blocks(num_cpu_blocks) File "/home/user/miniconda/lib/python3.9/site-packages/vllm/worker/cpu_worker.py", line 276, in _validate_num_cpu_blocks raise ValueError( ValueError: The model's max seq len (131072) is larger than the maximum number of tokens that can be stored in KV cache (37440). Try increasing `VLLM_CPU_KVCACHE_SPACE` or decreasing `max_model_len` when initializing the engine. Traceback (most recent call last): File "/home/user/miniconda/bin/vllm", line 8, in <module> sys.exit(main()) File "/home/user/miniconda/lib/python3.9/site-packages/vllm/scripts.py", line 165, in main args.dispatch_function(args) File "/home/user/miniconda/lib/python3.9/site-packages/vllm/scripts.py", line 37, in serve uvloop.run(run_server(args)) File "/home/user/miniconda/lib/python3.9/site-packages/uvloop/__init__.py", line 82, in run return loop.run_until_complete(wrapper()) File "uvloop/loop.pyx", line 1518, in uvloop.loop.Loop.run_until_complete File "/home/user/miniconda/lib/python3.9/site-packages/uvloop/__init__.py", line 61, in wrapper return await main File "/home/user/miniconda/lib/python3.9/site-packages/vllm/entrypoints/openai/api_server.py", line 538, in run_server async with build_async_engine_client(args) as engine_client: File "/home/user/miniconda/lib/python3.9/contextlib.py", line 181, in __aenter__ return await self.gen.__anext__() File "/home/user/miniconda/lib/python3.9/site-packages/vllm/entrypoints/openai/api_server.py", line 105, in build_async_engine_client async with build_async_engine_client_from_engine_args( File "/home/user/miniconda/lib/python3.9/contextlib.py", line 181, in __aenter__ return await self.gen.__anext__() File "/home/user/miniconda/lib/python3.9/site-packages/vllm/entrypoints/openai/api_server.py", line 192, in build_async_engine_client_from_engine_args raise RuntimeError( RuntimeError: Engine process failed to start

Container logs: