vcuda-controller
vcuda-controller copied to clipboard
I want to ask some question, and look forward to your reply. Cugetprocaddress is added in cuda-11.4, which can prevent our hijacking code from being executed. Have you solved this...
进入到 pod 里面 执行 nvidia-smi , 显示的显存 和 node 节点是一致, pod 里面应该显示 给pod 分配的资源吧
Why do I get an error when I start multiple GPU-resource pods simultaneously (concurrently) using vcuda? In vcuda loader.c, I add `ferror` to print `errno` related error message, I get...
1. why call cuInit() in initialization() and call initialization() in cuInit() ? 2. why call initialization() many times while only one call is need? (even use g_init_once to ensure it)
```c nvmlReturn_t nvmlDeviceSetComputeMode(nvmlDevice_t device, nvmlComputeMode_t mode) { if (g_anycuda_config.enable) { return NVML_ERROR_NOT_SUPPORTED; } return NVML_ENTRY_CALL(nvml_library_entry, nvmlDeviceSetComputeMode, device, mode); } ```
fix containerd cgroupfs path use `:` refactor the reading logic to simplify it.
I tried to use vcuda on Driver Version: 470.57.02, the program may fail without warning. Does it need to be updated for cuda11.4?Thanks!
**Describe the bug** When I was testing triton inference server 19.10, GPU memory usage increases when the following two functions are called: 1. cuCtxGetCurrent 2. cuModuleGetFunction It seems when loading...
I see the function https://github.com/tkestack/vcuda-controller/blob/5ec3fcbc58679bbbbd82ef9e21d647d8d7383876/src/hijack_call.c#L713-L731 so, should it be change to ```c request_size = base_size * pAllocateArray->NumChannels * pAllocateArray->Height * pAllocateArray->Width * pAllocateArray->Depth; ```
I tried to build vcuda by running `IMAGE_FILE={xx} ./build-img.sh` and get the /usr/bin/nvml-monitor以及/usr/lib64/libcuda-control.so. Now I want to run the container by docker run xx, so what should I do and...