baalajimaestro/ollama
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

Remove no longer supported max vram var

Browse source 
The OLLAMA_MAX_VRAM env var was a temporary workaround for OOM
scenarios.  With Concurrency this was no longer wired up, and the simplistic
value doesn't map to multi-GPU setups.  Users can still set `num_gpu`
to limit memory usage to avoid OOM if we get our predictions wrong.
This commit is contained in:
Daniel Hiltgen 2024-07-22 09:08:11 -07:00
parent 80ee9b5e47
commit cc269ba094
3 changed files with 2 additions and 16 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

1
cmd/cmd.go
View file

@ -1344,7 +1344,6 @@ func NewCLI() *cobra.Command {
envVars["OLLAMA_TMPDIR"],
envVars["OLLAMA_FLASH_ATTENTION"],
envVars["OLLAMA_LLM_LIBRARY"],
envVars["OLLAMA_MAX_VRAM"],
})
default:
appendEnvDocs(cmd, envs)

13
envconfig/config.go
View file

@ -43,8 +43,6 @@ var (
MaxRunners int
// Set via OLLAMA_MAX_QUEUE in the environment
MaxQueuedRequests int
// Set via OLLAMA_MAX_VRAM in the environment
MaxVRAM uint64
// Set via OLLAMA_MODELS in the environment
ModelsDir string
// Set via OLLAMA_NOHISTORY in the environment
@ -89,7 +87,6 @@ func AsMap() map[string]EnvVar {
"OLLAMA_LLM_LIBRARY": {"OLLAMA_LLM_LIBRARY", LLMLibrary, "Set LLM library to bypass autodetection"},
"OLLAMA_MAX_LOADED_MODELS": {"OLLAMA_MAX_LOADED_MODELS", MaxRunners, "Maximum number of loaded models per GPU"},
"OLLAMA_MAX_QUEUE": {"OLLAMA_MAX_QUEUE", MaxQueuedRequests, "Maximum number of queued requests"},
"OLLAMA_MAX_VRAM": {"OLLAMA_MAX_VRAM", MaxVRAM, "Maximum VRAM"},
"OLLAMA_MODELS": {"OLLAMA_MODELS", ModelsDir, "The path to the models directory"},
"OLLAMA_NOHISTORY": {"OLLAMA_NOHISTORY", NoHistory, "Do not preserve readline history"},
"OLLAMA_NOPRUNE": {"OLLAMA_NOPRUNE", NoPrune, "Do not prune model blobs on startup"},
@ -194,16 +191,6 @@ func LoadConfig() {
TmpDir = clean("OLLAMA_TMPDIR")
userLimit := clean("OLLAMA_MAX_VRAM")
if userLimit != "" {
avail, err := strconv.ParseUint(userLimit, 10, 64)
if err != nil {
slog.Error("invalid setting, ignoring", "OLLAMA_MAX_VRAM", userLimit, "error", err)
} else {
MaxVRAM = avail
}
}
LLMLibrary = clean("OLLAMA_LLM_LIBRARY")
if onp := clean("OLLAMA_NUM_PARALLEL"); onp != "" {

4
integration/concurrency_test.go
View file

@ -69,7 +69,7 @@ func TestIntegrationConcurrentPredictOrcaMini(t *testing.T) {
reqLimit := len(req)
iterLimit := 5
vram := os.Getenv("OLLAMA_MAX_VRAM")
vram := os.Getenv("OLLAMA_MAX_VRAM") // TODO - discover actual VRAM
if vram != "" {
max, err := strconv.ParseUint(vram, 10, 64)
require.NoError(t, err)
@ -106,7 +106,7 @@ func TestIntegrationConcurrentPredictOrcaMini(t *testing.T) {
// Stress the system if we know how much VRAM it has, and attempt to load more models than will fit
func TestMultiModelStress(t *testing.T) {
vram := os.Getenv("OLLAMA_MAX_VRAM")
vram := os.Getenv("OLLAMA_MAX_VRAM") // TODO - discover actual VRAM
if vram == "" {
t.Skip("OLLAMA_MAX_VRAM not specified, can't pick the right models for the stress test")
}