Verify permissions for AMD GPU (#6736)
This adds back a check which was lost many releases back to verify /dev/kfd permissions which when lacking, can lead to confusing failure modes of: "rocBLAS error: Could not initialize Tensile host: No devices found" This implementation does not hard fail the serve command but instead will fall back to CPU with an error log. In the future we can include this in the GPU discovery UX to show detected but unsupported devices we discovered.
This commit is contained in:
parent
735a0ca2e4
commit
9246e6dd15
2 changed files with 32 additions and 0 deletions
|
@ -91,6 +91,17 @@ If none of those resolve the problem, gather additional information and file an
|
||||||
- Check dmesg for any errors `sudo dmesg | grep -i nvrm` and `sudo dmesg | grep -i nvidia`
|
- Check dmesg for any errors `sudo dmesg | grep -i nvrm` and `sudo dmesg | grep -i nvidia`
|
||||||
|
|
||||||
|
|
||||||
|
## AMD GPU Discovery
|
||||||
|
|
||||||
|
On linux, AMD GPU access typically requires `video` and/or `render` group membership to access the `/dev/kfd` device. If permissions are not set up correctly, Ollama will detect this and report an error in the server log.
|
||||||
|
|
||||||
|
When running in a container, in some Linux distributions and container runtimes, the ollama process may be unable to access the GPU. Use `ls -ld /dev/kfd /dev/dri /dev/dri/*` on the host system to determine the group assignments on your system, and pass additional `--group-add ...` arguments to the container so it can access the required devices.
|
||||||
|
|
||||||
|
If you are experiencing problems getting Ollama to correctly discover or use your GPU for inference, the following may help isolate the failure.
|
||||||
|
- `AMD_LOG_LEVEL=3` Enable info log levels in the AMD HIP/ROCm libraries. This can help show more detailed error codes that can help troubleshoot problems
|
||||||
|
- `OLLAMA_DEBUG=1` During GPU discovery additional information will be reported
|
||||||
|
- Check dmesg for any errors from amdgpu or kfd drivers `sudo dmesg | grep -i amdgpu` and `sudo dmesg | grep -i kfd`
|
||||||
|
|
||||||
## Windows Terminal Errors
|
## Windows Terminal Errors
|
||||||
|
|
||||||
Older versions of Windows 10 (e.g., 21H1) are known to have a bug where the standard terminal program does not display control characters correctly. This can result in a long string of strings like `←[?25h←[?25l` being displayed, sometimes erroring with `The parameter is incorrect` To resolve this problem, please update to Win 10 22H1 or newer.
|
Older versions of Windows 10 (e.g., 21H1) are known to have a bug where the standard terminal program does not display control characters correctly. This can result in a long string of strings like `←[?25h←[?25l` being displayed, sometimes erroring with `The parameter is incorrect` To resolve this problem, please update to Win 10 22H1 or newer.
|
||||||
|
|
|
@ -5,6 +5,7 @@ import (
|
||||||
"errors"
|
"errors"
|
||||||
"fmt"
|
"fmt"
|
||||||
"io"
|
"io"
|
||||||
|
"io/fs"
|
||||||
"log/slog"
|
"log/slog"
|
||||||
"os"
|
"os"
|
||||||
"path/filepath"
|
"path/filepath"
|
||||||
|
@ -359,6 +360,10 @@ func AMDGetGPUInfo() []RocmGPUInfo {
|
||||||
if len(resp) == 0 {
|
if len(resp) == 0 {
|
||||||
slog.Info("no compatible amdgpu devices detected")
|
slog.Info("no compatible amdgpu devices detected")
|
||||||
}
|
}
|
||||||
|
if err := verifyKFDDriverAccess(); err != nil {
|
||||||
|
slog.Error("amdgpu devices detected but permission problems block access", "error", err)
|
||||||
|
return nil
|
||||||
|
}
|
||||||
return resp
|
return resp
|
||||||
}
|
}
|
||||||
|
|
||||||
|
@ -455,3 +460,19 @@ func getFreeMemory(usedFile string) (uint64, error) {
|
||||||
}
|
}
|
||||||
return usedMemory, nil
|
return usedMemory, nil
|
||||||
}
|
}
|
||||||
|
|
||||||
|
func verifyKFDDriverAccess() error {
|
||||||
|
// Verify we have permissions - either running as root, or we have group access to the driver
|
||||||
|
fd, err := os.OpenFile("/dev/kfd", os.O_RDWR, 0o666)
|
||||||
|
if err != nil {
|
||||||
|
if errors.Is(err, fs.ErrPermission) {
|
||||||
|
return fmt.Errorf("permissions not set up properly. Either run ollama as root, or add you user account to the render group. %w", err)
|
||||||
|
} else if errors.Is(err, fs.ErrNotExist) {
|
||||||
|
// Container runtime failure?
|
||||||
|
return fmt.Errorf("kfd driver not loaded. If running in a container, remember to include '--device /dev/kfd --device /dev/dri'")
|
||||||
|
}
|
||||||
|
return fmt.Errorf("failed to check permission on /dev/kfd: %w", err)
|
||||||
|
}
|
||||||
|
fd.Close()
|
||||||
|
return nil
|
||||||
|
}
|
||||||
|
|
Loading…
Reference in a new issue