RPR on top of causal attention #453
Draft
Conversation
This file contains 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: Alex Zinenko <[email protected]>
Signed-off-by: Nicolas Vasilache <[email protected]>
Signed-off-by: Nicolas Vasilache <[email protected]>
Signed-off-by: Nicolas Vasilache <[email protected]>
This revision uses `tkw.apply_expr` to circumvent type mismatches such as: ``` ValueError: Expected an fx.Node but got <class 'int'> ValueError: Expected an fx.Node but got <class 'Symbol'> ``` This further requires supporting index_cast in `tkw.cast` and playgroun/vanialla_attention.py now produces valid IR. Signed-off-by: Nicolas Vasilache <[email protected]>
Refactor and add default torch implementation against which we allclose. Set sizes to known good values that pass the checks; it is easy to fall off the cliff with various size combinations. Additionally, with the following, one can remove the inplace hack. ``` pip install -r pytorch-rocm-requirements.txt -e . ``` Signed-off-by: Nicolas Vasilache <[email protected]>
Signed-off-by: Nicolas Vasilache <[email protected]>
Signed-off-by: Alex Zinenko <[email protected]>
Signed-off-by: Nicolas Vasilache <[email protected]>
Signed-off-by: Nicolas Vasilache <[email protected]>
Signed-off-by: Stanley Winata <[email protected]>
Signed-off-by: Stanley Winata <[email protected]>
Signed-off-by: Stanley Winata <[email protected]>
Signed-off-by: Stanley Winata <[email protected]>
Signed-off-by: Stanley Winata <[email protected]>
Signed-off-by: Stanley Winata <[email protected]>
Signed-off-by: Stanley Winata <[email protected]>
Signed-off-by: Stanley Winata <[email protected]>
nicolasvasilache
force-pushed
the
rpe_on_top_of_stans
branch
2 times, most recently
from
06180db to
42a7fb4
Compare
Signed-off-by: Nicolas Vasilache <[email protected]>
nicolasvasilache
force-pushed
the
rpe_on_top_of_stans
branch
from
42a7fb4 to
cc8bf31
Compare
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.