refact cuda ut to facilitate automation #559
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Signed-off-by: n1ck-guo <[email protected]>
for more information, see https://pre-commit.ci
wenhuach21
reviewed
May 12, 2025
wenhuach21
reviewed
May 12, 2025
wenhuach21
reviewed
May 12, 2025
wenhuach21
reviewed
May 12, 2025
Signed-off-by: n1ck-guo <[email protected]>
Signed-off-by: n1ck-guo <[email protected]>
Signed-off-by: Sun, Xuehao <[email protected]>
Signed-off-by: n1ck-guo <[email protected]>
XuehaoSun
approved these changes
May 14, 2025
Signed-off-by: n1ck-guo <[email protected]>
wenhuach21
reviewed
May 14, 2025
wenhuach21
reviewed
May 14, 2025
XuehaoSun
requested changes
May 16, 2025
XuehaoSun
requested changes
May 16, 2025
XuehaoSun
requested changes
May 16, 2025
Signed-off-by: n1ck-guo <[email protected]>
Signed-off-by: n1ck-guo <[email protected]>
Signed-off-by: n1ck-guo <[email protected]>
Signed-off-by: n1ck-guo <[email protected]>
Signed-off-by: Sun, Xuehao <[email protected]>
Signed-off-by: n1ck-guo <[email protected]>
Signed-off-by: n1ck-guo <[email protected]>
Signed-off-by: n1ck-guo <[email protected]>
Signed-off-by: n1ck-guo <[email protected]>
Signed-off-by: n1ck-guo <[email protected]>
wenhuach21
reviewed
May 29, 2025
auto_round/data_type/int.py
Outdated
| @@ -134,10 +134,13 @@ def quant_tensor_sym_dq( | |||
|
|
|||
| scale = scale.view(-1, 1) | |||
| zp = torch.full_like(scale, maxq) # pylint: disable=E1130 | |||
| scale = torch.where(scale < 0, torch.clamp(scale, max=-q_scale_thresh), torch.clamp(scale, min=q_scale_thresh)) | |||
There was a problem hiding this comment.
Why are you using full-range symmetric quantization here? As I mentioned earlier, it may not be well-suited for double quantization. Do you have any accuracy data to support this choice?
wenhuach21
reviewed
May 29, 2025
auto_round/data_type/int.py
Outdated
| int_w = round_ste(tensor / scale + v) | ||
| q = torch.clamp(int_w + zp, 0, 2 ** bits - 1) | ||
| qdq_result = (scale * (q - zp)).to(tensor.dtype) | ||
| qdq_result = revert_tensor_by_pad(qdq_result, orig_shape=orig_shape, pad_len=pad_len) | ||
| if qdq_result.isnan().sum() > 0: | ||
| breakpoint() |
Signed-off-by: n1ck-guo <[email protected]>
XuehaoSun
approved these changes
May 29, 2025
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
No description provided.