graph: backend: dnnl: sdpa v1 kernel support quantize SDPA and backend refactor #3334
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
xiang1guo
force-pushed
the
xiang/main/int8-internal-sdpa
branch
from
6f82e35 to
0f9aa9a
Compare
xiang1guo
changed the title
xiang1guo
changed the title
|
We have alternative solution in #3423 |
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Outdated suggestions cannot be applied.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.
Background
This is a follow-up work based on #2930 and #2931. The PR mainly focuses on supporting quantized SDPA with internal dnnl_sdpa. It helps to reduce graph compilation time and also simplifies the backend optimization pass.
Works
sdp_primitive_kernel_tandsdp_primitive_v1_kernel_tTODO
Fused graph
compressed SDPA dot graph:
before fusion
after fusion
legacy GQA dot graph
before fusion
after fusion