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

2
convert/reader.go
View File

@@ -33,8 +33,8 @@ func (t tensorBase) Shape() []uint64 {
const (
tensorKindFP32 uint32 = iota
tensorKindFP16
tensorKindMXFP4 = 4
tensorKindBF16 = 30
tensorKindMXFP4 = 39
)
func (t tensorBase) Kind() uint32 {