RTX 4090 error when using demo1

[xixingya]

Traceback (most recent call last):
File "/usr/local/bin/lmcache_vllm", line 5, in
from lmcache_vllm.script import main
File "/usr/local/lib/python3.12/dist-packages/lmcache_vllm/init.py", line 4, in
from lmcache_vllm.vllm_injection import InitLMCacheEnvironment
File "/usr/local/lib/python3.12/dist-packages/lmcache_vllm/vllm_injection.py", line 15, in
from lmcache_vllm.vllm_adapter import (lmcache_get_config,
File "/usr/local/lib/python3.12/dist-packages/lmcache_vllm/vllm_adapter.py", line 32, in
LMCACHE_CUDA_STREAM = torch.cuda.Stream()
^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.12/dist-packages/torch/cuda/streams.py", line 35, in new
return super().new(cls, priority=priority, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
RuntimeError: CUDA error: forward compatibility was attempted on non supported HW
CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.
For debugging consider passing CUDA_LAUNCH_BLOCKING=1
Device-side assertions were explicitly omitted for this error check; the error probably arose while initializing the DSA handlers.

[xixingya]

this is because my host machine using cuda 12.2 and the container using cuda 12.4