matt/ollama37
1
0
Fork 0
mirror of https://github.com/dogkeeper886/ollama37.git synced 2025-12-10 07:46:59 +00:00
Code Issues Packages Projects Releases Wiki Activity

Introduce GPU Overhead env var (#5922)

Browse Source 
Provide a mechanism for users to set aside an amount of VRAM on each GPU
to make room for other applications they want to start after Ollama, or workaround
memory prediction bugs
This commit is contained in:
Daniel Hiltgen
2024-09-05 13:46:35 -07:00
committed by GitHub
parent a60d9b89ce
commit b05c9e83d9
3 changed files with 28 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
envconfig/config.go
View File

@@ -231,6 +231,25 @@ var (
MaxVRAM = Uint("OLLAMA_MAX_VRAM", 0)
)
func Uint64(key string, defaultValue uint64) func() uint64 {
return func() uint64 {
if s := Var(key); s != "" {
if n, err := strconv.ParseUint(s, 10, 64); err != nil {
slog.Warn("invalid environment variable, using default", "key", key, "value", s, "default", defaultValue)
} else {
return n
}
}
return defaultValue
}
}
var (
// Set aside VRAM per GPU
GpuOverhead = Uint64("OLLAMA_GPU_OVERHEAD", 0)
)
type EnvVar struct {
Name string
Value any
@@ -241,6 +260,7 @@ func AsMap() map[string]EnvVar {
ret := map[string]EnvVar{
"OLLAMA_DEBUG": {"OLLAMA_DEBUG", Debug(), "Show additional debug information (e.g. OLLAMA_DEBUG=1)"},
"OLLAMA_FLASH_ATTENTION": {"OLLAMA_FLASH_ATTENTION", FlashAttention(), "Enabled flash attention"},
"OLLAMA_GPU_OVERHEAD": {"OLLAMA_GPU_OVERHEAD", GpuOverhead(), "Reserve a portion of VRAM per GPU (bytes)"},
"OLLAMA_HOST": {"OLLAMA_HOST", Host(), "IP Address for the ollama server (default 127.0.0.1:11434)"},
"OLLAMA_KEEP_ALIVE": {"OLLAMA_KEEP_ALIVE", KeepAlive(), "The duration that models stay loaded in memory (default \"5m\")"},
"OLLAMA_LLM_LIBRARY": {"OLLAMA_LLM_LIBRARY", LLMLibrary(), "Set LLM library to bypass autodetection"},