reanimator/bee
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 1 Wiki Activity

Add NVIDIA stress loader selection and DCGM 4 support

Browse Source
This commit is contained in:
Mikhail Chusavitin
2026-03-31 11:15:15 +03:00
parent 20f834aa96
commit 6dee8f3509
31 changed files with 789 additions and 111 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
audit/internal/platform/runtime.go
View File

@@ -136,7 +136,8 @@ func (s *System) runtimeToolStatuses(vendor string) []ToolStatus {
tools = append(tools, s.CheckTools([]string{
"nvidia-smi",
"nvidia-bug-report.sh",
"bee-gpu-stress",
"bee-gpu-burn",
"bee-john-gpu-stress",
})...)
case "amd":
tool := ToolStatus{Name: "rocm-smi"}
@@ -176,8 +177,8 @@ func (s *System) collectGPURuntimeHealth(vendor string, health *schema.RuntimeHe
health.DriverReady = true
}
if lookErr := exec.Command("sh", "-c", "command -v bee-gpu-stress >/dev/null 2>&1").Run(); lookErr == nil {
out, err := exec.Command("bee-gpu-stress", "--seconds", "1", "--size-mb", "1").CombinedOutput()
if _, lookErr := exec.LookPath("bee-gpu-burn"); lookErr == nil {
out, err := exec.Command("bee-gpu-burn", "--seconds", "1", "--size-mb", "1").CombinedOutput()
if err == nil {
health.CUDAReady = true
} else if strings.Contains(strings.ToLower(string(out)), "cuda_error_system_not_ready") {