Skip to content

Fix global dequantize buffer dtype mismatch across mixed-precision loads #4026

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

Merged
danielhanchen merged 1 commit into from
Mar 1, 2026
Merged

Fix global dequantize buffer dtype mismatch across mixed-precision loads #4026

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
4 changes: 2 additions & 2 deletions unsloth/kernels/utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -388,7 +388,7 @@ def fast_dequantize(W, quant_state = None, out = None, use_global_buffer = False
global ABSMAX_BUFFERS
WEIGHT_BUFFER = WEIGHT_BUFFERS[device_index]
ABSMAX_BUFFER = ABSMAX_BUFFERS[device_index]
if WEIGHT_BUFFER is None:
if WEIGHT_BUFFER is None or WEIGHT_BUFFER.dtype != dtype:
WEIGHT_BUFFERS[device_index] = WEIGHT_BUFFER = torch_empty(
size, dtype = dtype, device = device, requires_grad = False
)
Expand Down Expand Up @@ -498,7 +498,7 @@ def fast_dequantize(W, quant_state = None, out = None, use_global_buffer = False
global ABSMAX_BUFFERS
WEIGHT_BUFFER = WEIGHT_BUFFERS[device_index]
ABSMAX_BUFFER = ABSMAX_BUFFERS[device_index]
if WEIGHT_BUFFER is None:
if WEIGHT_BUFFER is None or WEIGHT_BUFFER.dtype != dtype:
WEIGHT_BUFFERS[device_index] = WEIGHT_BUFFER = torch_empty(
size, dtype = dtype, device = device, requires_grad = False
)
Expand Down