matt/ollama37
1
0
Fork 0
mirror of https://github.com/dogkeeper886/ollama37.git synced 2025-12-11 08:17:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

Move quantization to new backend (#10363)

Browse Source 
* Move quantization logic to GGML via new backend

This moves the model aware logic to Go code and calls GGMLs quantization code for model creation.

* Remove "add model quantizations"

This is no longer needed now that quantization is implemented in Go+GGML code directly.
This commit is contained in:
Daniel Hiltgen
2025-05-06 11:20:48 -07:00
committed by GitHub
parent 95e744beeb
commit 424810450f
39 changed files with 1854 additions and 440 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
integration/model_arch_test.go
View File

@@ -48,17 +48,6 @@ var (
}
)
func getTimeouts(t *testing.T) (soft time.Duration, hard time.Duration) {
deadline, hasDeadline := t.Deadline()
if !hasDeadline {
return 8 * time.Minute, 10 * time.Minute
} else if deadline.Compare(time.Now().Add(2*time.Minute)) <= 0 {
t.Skip("too little time")
return time.Duration(0), time.Duration(0)
}
return -time.Since(deadline.Add(-2 * time.Minute)), -time.Since(deadline.Add(-20 * time.Second))
}
func TestModelsGenerate(t *testing.T) {
softTimeout, hardTimeout := getTimeouts(t)
slog.Info("Setting timeouts", "soft", softTimeout, "hard", hardTimeout)