mirrors/ollama
1
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2025-05-11 18:36:41 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

Detect AMD GPU info via sysfs and block old cards

Browse source 
This wires up some new logic to start using sysfs to discover AMD GPU
information and detects old cards we can't yet support so we can fallback to CPU mode.
This commit is contained in:
Daniel Hiltgen 2024-02-11 14:50:06 -08:00
parent 1c8435ffa9
commit 6d84f07505
5 changed files with 151 additions and 34 deletions
Download patch file Download diff file Expand all files Collapse all files

86
gpu/gpu.go
View file

@ -149,43 +149,63 @@ func GetGPUInfo() GpuInfo {
slog.Info(fmt.Sprintf("CUDA GPU is too old. Falling back to CPU mode. Compute Capability detected: %d.%d", cc.major, cc.minor))
}
}
} else if gpuHandles.rocm != nil && (cpuVariant != "" || runtime.GOARCH != "amd64") {
C.rocm_check_vram(*gpuHandles.rocm, &memInfo)
if memInfo.err != nil {
slog.Info(fmt.Sprintf("error looking up ROCm GPU memory: %s", C.GoString(memInfo.err)))
C.free(unsafe.Pointer(memInfo.err))
} else if memInfo.igpu_index >= 0 && memInfo.count == 1 {
// Only one GPU detected and it appears to be an integrated GPU - skip it
slog.Info("ROCm unsupported integrated GPU detected")
} else if memInfo.count > 0 {
if memInfo.igpu_index >= 0 {
// We have multiple GPUs reported, and one of them is an integrated GPU
// so we have to set the env var to bypass it
// If the user has specified their own ROCR_VISIBLE_DEVICES, don't clobber it
val := os.Getenv("ROCR_VISIBLE_DEVICES")
if val == "" {
devices := []string{}
for i := 0; i < int(memInfo.count); i++ {
if i == int(memInfo.igpu_index) {
continue
} else if AMDDetected() && gpuHandles.rocm != nil && (cpuVariant != "" || runtime.GOARCH != "amd64") {
ver, err := AMDDriverVersion()
if err == nil {
slog.Info("AMD Driver: " + ver)
}
gfx := AMDGFXVersions()
tooOld := false
for _, v := range gfx {
if v.Major < 9 {
slog.Info("AMD GPU too old, falling back to CPU " + v.ToGFXString())
tooOld = true
break
}
// TODO - remap gfx strings for unsupporetd minor/patch versions to supported for the same major
// e.g. gfx1034 works if we map it to gfx1030 at runtime
}
if !tooOld {
// TODO - this algo can be shifted over to use sysfs instead of the rocm info library...
C.rocm_check_vram(*gpuHandles.rocm, &memInfo)
if memInfo.err != nil {
slog.Info(fmt.Sprintf("error looking up ROCm GPU memory: %s", C.GoString(memInfo.err)))
C.free(unsafe.Pointer(memInfo.err))
} else if memInfo.igpu_index >= 0 && memInfo.count == 1 {
// Only one GPU detected and it appears to be an integrated GPU - skip it
slog.Info("ROCm unsupported integrated GPU detected")
} else if memInfo.count > 0 {
if memInfo.igpu_index >= 0 {
// We have multiple GPUs reported, and one of them is an integrated GPU
// so we have to set the env var to bypass it
// If the user has specified their own ROCR_VISIBLE_DEVICES, don't clobber it
val := os.Getenv("ROCR_VISIBLE_DEVICES")
if val == "" {
devices := []string{}
for i := 0; i < int(memInfo.count); i++ {
if i == int(memInfo.igpu_index) {
continue
}
devices = append(devices, strconv.Itoa(i))
}
devices = append(devices, strconv.Itoa(i))
val = strings.Join(devices, ",")
os.Setenv("ROCR_VISIBLE_DEVICES", val)
}
val = strings.Join(devices, ",")
os.Setenv("ROCR_VISIBLE_DEVICES", val)
slog.Info(fmt.Sprintf("ROCm integrated GPU detected - ROCR_VISIBLE_DEVICES=%s", val))
}
slog.Info(fmt.Sprintf("ROCm integrated GPU detected - ROCR_VISIBLE_DEVICES=%s", val))
resp.Library = "rocm"
var version C.rocm_version_resp_t
C.rocm_get_version(*gpuHandles.rocm, &version)
verString := C.GoString(version.str)
if version.status == 0 {
resp.Variant = "v" + verString
} else {
slog.Info(fmt.Sprintf("failed to look up ROCm version: %s", verString))
}
C.free(unsafe.Pointer(version.str))
}
resp.Library = "rocm"
var version C.rocm_version_resp_t
C.rocm_get_version(*gpuHandles.rocm, &version)
verString := C.GoString(version.str)
if version.status == 0 {
resp.Variant = "v" + verString
} else {
slog.Info(fmt.Sprintf("failed to look up ROCm version: %s", verString))
}
C.free(unsafe.Pointer(version.str))
}
}
if resp.Library == "" {