Skip to content

Support/ideogram gguf #1

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
fractal-fumbler wants to merge 6 commits into from
Closed

Support/ideogram gguf #1

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
cb1585c
Add Ideogram architecture detection in convert.py
molbal Jun 9, 2026
db3b45e
Add Ideogram to IMG_ARCH_LIST in loader.py
molbal Jun 9, 2026
61dde54
Add dequantization handling for Ideogram inference
molbal Jun 9, 2026
fd65e64
Fix BF16 tensor dequantization logic
molbal Jun 9, 2026
e4c7598
Refactor dequantization functions and imports
molbal Jun 9, 2026
b111cdb
Add newline at end of convert.py
molbal Jun 9, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 3 additions & 0 deletions dequant.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,6 +18,9 @@ def dequantize_tensor(tensor, dtype=None, dequant_dtype=None):

if qtype in TORCH_COMPATIBLE_QTYPES:
return tensor.to(dtype)
elif qtype == gguf.GGMLQuantizationType.BF16:
tensor = torch.Tensor(tensor.data.view(torch.bfloat16).reshape(oshape))
return tensor if dtype is None or dtype == torch.bfloat16 else tensor.to(dtype)
elif qtype in dequantize_functions:
dequant_dtype = dtype if dequant_dtype == "target" else dequant_dtype
return dequantize(tensor.data, qtype, oshape, dtype=dequant_dtype).to(dtype)
Expand Down
Loading