{
    "BackendConfig": {
        "ModelDeployConfig": {
            "ModelConfig": [
                {
                    "dp": 4,
                    "tp": 8,
                    "moe_tp": 1,
                    "moe_ep": 32
                }
            ]
        }
    }
}

# cat /usr/local/Ascend/driver/version.info
Version=24.1.rc2.2
ascendhal_version=7.35.23
aicpu_version=1.0
tdt_version=1.0
log_version=1.0
prof_version=2.0
dvppkernels_version=1.1
tsfw_version=1.0
Innerversion=V100R001C18SPC001B233
compatible_version=[V100R001C30],[V100R001C13],[V100R001C15],[V100R001C17],[V100R001C18]
compatible_version_fw=[7.0.0,7.2.99]
package_version=24.1.rc2.2

Daemon start success!

curl --location 'http://172.20.84.67:1025/v1/chat/completions' \
--header 'Content-Type: application/json' \
--data '
{
    "model": "deepseek-v3",
    "messages": [{
        "role": "user",
        "content": "who are you?"
    }]
}
'

[error] [1079] [multi_latent_attention_operation.cpp:91] headNum should be {8,16,32,64,128}

"dtype": "fp8"

"dtype": "bf16"

"quant_method": "fp8"

"quant_method": "bf16"