highperfocused/ollama
1
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2025-11-11 01:37:30 +01:00
Code Issues Packages Projects Releases Wiki Activity

feat: incremental gguf parser (#10822)

Browse Source 
* incremental gguf parser
* gguf: update test to not rely on gguf on disc
* re-use existing create gguf
* read capabilities from gguf kv
* kv exists
* update tests
* s/doneFunc/successFunc/g
* new buffered reader

---------

Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>
This commit is contained in:
Michael Yang
2025-06-12 11:04:11 -07:00
committed by GitHub
parent 45f56355d5
commit 6b04cad7e8
13 changed files with 1357 additions and 164 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
server/quantization_test.go
View File

@@ -257,16 +257,8 @@ func TestQuantizeModel(t *testing.T) {
for _, tt := range cases {
t.Run(tt.name, func(t *testing.T) {
f, err := os.CreateTemp(t.TempDir(), tt.name)
if err != nil {
t.Fatal(err.Error())
}
defer f.Close()
err = fsggml.WriteGGUF(f, tt.kv, tt.tensors)
if err != nil {
t.Fatalf("failed to create initial model: %s", err)
}
fp, err := os.Open(f.Name())
p, _ := createBinFile(t, tt.kv, tt.tensors)
fp, err := os.Open(p)
if err != nil {
t.Fatal(err.Error())
}