INFO 02-14 19:02:46 [__init__.py:245] Automatically detected platform cuda. Warning: The nvmlDeviceGetCudaComputeCapability is currently not supported.The nvmlDeviceGetCudaComputeCapability is invalid. Traceback (most recent call last): File "/root/miniconda3/envs/vllm_local/bin/vllm", line 3, in from vllm.entrypoints.cli.main import main File "/root/miniconda3/envs/vllm_local/lib/python3.10/site-packages/vllm/entrypoints/cli/__init__.py", line 3, in from vllm.entrypoints.cli.benchmark.latency import BenchmarkLatencySubcommand File "/root/miniconda3/envs/vllm_local/lib/python3.10/site-packages/vllm/entrypoints/cli/benchmark/latency.py", line 5, in from vllm.benchmarks.latency import add_cli_args, main File "/root/miniconda3/envs/vllm_local/lib/python3.10/site-packages/vllm/benchmarks/latency.py", line 16, in from vllm import LLM, SamplingParams File "", line 1075, in _handle_fromlist File "/root/miniconda3/envs/vllm_local/lib/python3.10/site-packages/vllm/__init__.py", line 64, in __getattr__ module = import_module(module_name, __package__) File "/root/miniconda3/envs/vllm_local/lib/python3.10/importlib/__init__.py", line 126, in import_module return _bootstrap._gcd_import(name[level:], package, level) File "/root/miniconda3/envs/vllm_local/lib/python3.10/site-packages/vllm/entrypoints/llm.py", line 22, in module from vllm.engine.arg_utils import (EngineArgs, HfOverrides, PoolerConfig, File "/root/miniconda3/envs/vllm_local/lib/python3.10/site-packages/vllm/engine/arg_utils.py", line 37, in from vllm.executor.executor_base import ExecutorBase File "/root/miniconda3/envs/vllm_local/lib/python3.10/site-packages/vllm/executor/executor_base.py", line 21, in from vllm.worker.worker_base import WorkerBase File "/root/miniconda3/envs/vllm_local/lib/python3.10/site-packages/vllm/worker/worker_base.py", line 26, in from vllm.worker.cache_engine import CacheEngine File "/root/miniconda3/envs/vllm_local/lib/python3.10/site-packages/vllm/worker/cache_engine.py", line 13, inmodule from vllm.attention.backends.tree_decoding_utils import move_cache File "/root/miniconda3/envs/vllm_local/lib/python3.10/site-packages/vllm/attention/backends/tree_decoding_utils.py", line 4, in module from vllm.attention.backends.blocksparse_attn import BlocksparseFlashAttentionImpl File "/root/miniconda3/envs/vllm_local/lib/python3.10/site-packages/vllm/attention/backends/blocksparse_attn.py", line 14, in module from vllm.attention.ops.blocksparse_attention.interface import ( File "/root/miniconda3/envs/vllm_local/lib/python3.10/site-packages/vllm/attention/ops/blocksparse_attention/interface.py", line 13, in module IS_COMPUTE_8_OR_ABOVE = current_platform.has_device_capability(80) File "/root/miniconda3/envs/vllm_local/lib/python3.10/site-packages/vllm/platforms/cuda.py", line 46, in wrapper return fn(*args, **kwargs) File "/root/miniconda3/envs/vllm_local/lib/python3.10/site-packages/vllm/platforms/cuda.py", line 453, in has_device_capability return super().has_device_capability(capability, device_id) File "/root/miniconda3/envs/vllm_local/lib/python3.10/site-packages/vllm/platforms/interface.py", line 222, in has_device_capability current_capability = cls.get_device_capability(device_id=device_id) File "/root/miniconda3/envs/vllm_local/lib/python3.10/site-packages/vllm/platforms/cuda.py", line 46, in wrapper return fn(*args, **kwargs) File "/root/miniconda3/envs/vllm_local/lib/python3.10/site-packages/vllm/platforms/cuda.py", line 440, in get_device_capability major, minor = pynvml.nvmlDeviceGetCudaComputeCapability(handle) File "/root/miniconda3/envs/vllm_local/lib/python3.10/site-packages/vllm/third_party/pynvml.py", line 3223, in nvmlDeviceGetCudaComputeCapability _nvmlCheckReturn(ret) File "/root/miniconda3/envs/vllm_local/lib/python3.10/site-packages/vllm/third_party/pynvml.py", line 1047, in _nvmlCheckReturn raise NVMLError(ret) vllm.third_party.pynvml.NVMLError_NotSupported: Not Supported