Skip to content

fix qwix bug #271

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
susanbao merged 2 commits into from
Oct 20, 2025
Merged

fix qwix bug #271

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
a65aa9a
fix qwix bug
susanbao Oct 20, 2025
ead8dfc
fix unit test
susanbao Oct 20, 2025
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
2 changes: 0 additions & 2 deletions src/maxdiffusion/pipelines/wan/wan_pipeline.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -297,7 +297,6 @@ def get_fp8_config(cls, config: HyperParameters):
weight_qtype=jnp.float8_e4m3fn,
act_qtype=jnp.float8_e4m3fn,
bwd_qtype=jnp.float8_e5m2,
bwd_use_original_residuals=True,
disable_channelwise_axes=True, # per_tensor calibration
weight_calibration_method=config.quantization_calibration_method,
act_calibration_method=config.quantization_calibration_method,
Expand All @@ -309,7 +308,6 @@ def get_fp8_config(cls, config: HyperParameters):
weight_qtype=jnp.float8_e4m3fn, # conv_general_dilated requires the same dtypes
act_qtype=jnp.float8_e4m3fn,
bwd_qtype=jnp.float8_e4m3fn,
bwd_use_original_residuals=True,
disable_channelwise_axes=True, # per_tensor calibration
weight_calibration_method=config.quantization_calibration_method,
act_calibration_method=config.quantization_calibration_method,
Expand Down
2 changes: 0 additions & 2 deletions src/maxdiffusion/tests/wan_transformer_test.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -342,7 +342,6 @@ def create_real_rule_instance(*args, **kwargs):
weight_qtype=jnp.float8_e4m3fn,
act_qtype=jnp.float8_e4m3fn,
bwd_qtype=jnp.float8_e5m2,
bwd_use_original_residuals=True,
disable_channelwise_axes=True, # per_tensor calibration
weight_calibration_method=config_fp8_full.quantization_calibration_method,
act_calibration_method=config_fp8_full.quantization_calibration_method,
Expand All @@ -354,7 +353,6 @@ def create_real_rule_instance(*args, **kwargs):
weight_qtype=jnp.float8_e4m3fn,
act_qtype=jnp.float8_e4m3fn,
bwd_qtype=jnp.float8_e4m3fn,
bwd_use_original_residuals=True,
disable_channelwise_axes=True, # per_tensor calibration
weight_calibration_method=config_fp8_full.quantization_calibration_method,
act_calibration_method=config_fp8_full.quantization_calibration_method,
Expand Down
Loading