OpenCL: Add group_norm, concat, tsembd, upscale, tanh, pad and repeat #13781
+1,309
−1
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Outdated suggestions cannot be applied.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.
This PR adds the following ops to OpenCL:
GROUP_NORM
CONCAT
TIMESTEP_EMBEDDING
UPSCALE
(both nearest and bilinear)UNARY_OP_TANH
PAD
REPEAT
With these additions, OpenCL now (hopefully) supports all the ops used in stable-diffusion.cpp.
All tests passed using
test-backend-ops
. Tested on: Adreno 750, 740, 730Note: I noticed that some
im2col
andrope
tests fail on Adreno 740 and 730. These issues existed prior to this PR and may need to be addressed in the future@lhez @max-krasnyansky