Add symmetric quantization with no clipping error in the tensor subclass based API #845
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
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/ao/845
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit d2d2af4 with merge base 1b317f9 ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
jerryzh168
reviewed
Sep 9, 2024
jerryzh168
reviewed
Sep 9, 2024
iseeyuan
force-pushed
the
newapi
branch
2 times, most recently
from
9b1120b to
3b9324e
Compare
jerryzh168
reviewed
Sep 9, 2024
| return to_affine_quantized_intx(x, mapping_type, _get_per_token_block_size(x), target_dtype) | ||
|
|
||
| def apply_int8_dynamic_activation_int4_weight_quant(weight, group_size=32): | ||
| def apply_int8_dynamic_activation_int4_weight_quant(weight, group_size=32, mapping_type=MappingType.SYMMETRIC): |
There was a problem hiding this comment.
might be better to clarify this is weight_mapping_type I feel
|
@iseeyuan although the merging is not blocked, please still wait for an approval before merging next time :) |
yanbing-j
pushed a commit
to yanbing-j/ao
that referenced
this pull request
Dec 9, 2024
* Initial move of browser GUI related files * Fix css reference issue * Remove moved file
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Outdated suggestions cannot be applied.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.
Follow up with #805 , add the same option to the new tensor subclass API.