mirrors/ollama
1
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2025-05-11 10:26:53 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

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
Download patch file Download diff file Expand all files Collapse all files

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")
}