run llama3-70B-q8_0 error

[leoHostProject]

What is the issue?

api call error
message:
{"error":{"message":"timed out waiting for llama runner to start:CUDA error:uncorrectable ECC error encountered
n current device:0,in function ggml cuda_compute_forward at /go/src/github.com/ollama/ollama/11m/1lama.cpp/ggml
-cuda.cu:2300\n err\nGGML_ASSERT:/go/src/github.com/ollama/ollama/11m/1lama.cpp/ggml-cuda.cu:60:!"CUDA error"
""type":"api_error","param"null,"code":null}}

OS

Linux, Docker

GPU

Nvidia

CPU

Intel

Ollama version

No response