highperfocused/ollama
1
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2025-11-11 09:17:50 +01:00
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

6
cmd/cmd.go
View File

@@ -162,7 +162,11 @@ func CreateHandler(cmd *cobra.Command, args []string) error {
if resp.Digest != "" {
bar, ok := bars[resp.Digest]
if !ok {
bar = progress.NewBar(fmt.Sprintf("pulling %s...", resp.Digest[7:19]), resp.Total, resp.Completed)
msg := resp.Status
if msg == "" {
msg = fmt.Sprintf("pulling %s...", resp.Digest[7:19])
}
bar = progress.NewBar(msg, resp.Total, resp.Completed)
bars[resp.Digest] = bar
p.Add(resp.Digest, bar)
}