mirrors/ollama-for-amd
1
0
Fork 0
mirror of https://github.com/likelovewant/ollama-for-amd.git synced 2025-12-21 22:33:56 +00:00
Code Issues Packages Projects Releases Wiki Activity

convert(gptoss): mxfp4 to ggml layout to avoid jit conversion (#12018)

Browse Source 
* convert: return bytes written

* ggml flavor mxfp4

* simplify jit conversion

* comment
This commit is contained in:
Michael Yang
2025-08-26 16:41:02 -07:00
committed by GitHub
parent 86834a2797
commit 59412fbb43
6 changed files with 49 additions and 58 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
convert/reader_safetensors.go
View File

@@ -188,17 +188,17 @@ func (st safetensor) WriteTo(w io.Writer) (int64, error) {
switch st.Kind() {
case tensorKindFP32:
return 0, binary.Write(w, binary.LittleEndian, f32s)
return int64(len(f32s) * 4), binary.Write(w, binary.LittleEndian, f32s)
case tensorKindFP16:
f16s := make([]uint16, len(f32s))
for i := range f32s {
f16s[i] = float16.Fromfloat32(f32s[i]).Bits()
}
return 0, binary.Write(w, binary.LittleEndian, f16s)
return int64(len(f16s) * 2), binary.Write(w, binary.LittleEndian, f16s)
case tensorKindBF16:
u8s := bfloat16.EncodeFloat32(f32s)
return 0, binary.Write(w, binary.LittleEndian, u8s)
return int64(len(u8s)), binary.Write(w, binary.LittleEndian, u8s)
default:
return 0, fmt.Errorf("unknown storage type: %d", st.Kind())
}