quant : allow quantization for LFM3-Audio codec decoder (#31386)

* quantize : quantize the LFM3-Audio codec decoder, it is Q4_0 QAT

* quantize : drop the QAT note from the LFM3-Audio comment
This commit is contained in:
Tarek Dakhran authored and GitHub committed 2026-10-30 11:52:59 +01:00
1 parent 1ab23c33b7
commit 889f2ec96d
2 files changed
+2 -5

No files matched your search

-3
View File
@@ -453,9 +453,6 @@ class LFM3AudioMmprojModel(MmprojModel):
def tensor_force_quant(self, name, new_name, bid, n_dims):
if new_name.startswith("a.conv1d.") or "conv_dw" in new_name or new_name.startswith("a.gen.wav.quant."):
return gguf.GGMLQuantizationType.F32
# the codec decoder is small and its log-magnitude/phase output does not survive quantization
if new_name.startswith("a.gen.wav."):
return gguf.GGMLQuantizationType.F16
return super().tensor_force_quant(name, new_name, bid, n_dims)
def generate_extra_tensors(self) -> Iterable[tuple[str, Tensor]]: