highperfocused/ollama
1
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2025-09-26 22:57:09 +02:00
Code Issues Packages Projects Releases Wiki Activity

llm: introduce k/v context quantization (vRAM improvements) (#6279)

Browse Source
This commit is contained in:
Sam
2024-12-04 10:57:19 +11:00
committed by GitHub
parent 2b82c5a8a1
commit 1bdab9fdb1
10 changed files with 147 additions and 21 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
llm/memory_test.go
View File

@@ -15,6 +15,7 @@ import (
func TestEstimateGPULayers(t *testing.T) {
t.Setenv("OLLAMA_DEBUG", "1")
t.Setenv("OLLAMA_KV_CACHE_TYPE", "") // Ensure default f16
modelName := "dummy"
f, err := os.CreateTemp(t.TempDir(), modelName)