Out variant for embedding_bag_4bit_rowwise_offsets #51324
Closed
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
💊 CI failures summary and remediationsAs of commit 84d3173 (more details on the Dr. CI page):
Extra GitHub checks: 1 failed
This comment was automatically generated by Dr. CI (expand for details).Follow this link to opt-out of these comments for your Pull Requests.Please report bugs/suggestions to the (internal) Dr. CI Users group. |
facebook-github-bot
added
cla signed
oncall: jit
|
This pull request was exported from Phabricator. Differential Revision: D26138322 |
Codecov Report
@@ Coverage Diff @@
## master #51324 +/- ##
=======================================
Coverage 80.85% 80.86%
=======================================
Files 1938 1938
Lines 211184 211189 +5
=======================================
+ Hits 170758 170770 +12
+ Misses 40426 40419 -7 |
Summary: Pull Request resolved: pytorch#51324 Add out variant for embedding_bag_4bit_rowwise_offsets and add it to static runtime registry Test Plan: ``` MKL_NUM_THREADS=1 OMP_NUM_THREADS=1 numactl -m 0 -C 1 buck-out/opt/gen/caffe2/caffe2/fb/predictor/ptvsc2_predictor_bench --scripted_model=$INLINE_CVR_DIR/210494966_0.predictor.disagg.remote_request_only_remote_cast.pt --pt_inputs=$INLINE_CVR_DIR/remote_ro_wrapped_input_data.pt --pt_enable_static_runtime=true --pt_cleanup_activations=true --pt_enable_out_variant=true --compare_results=true --iters=5000 --warmup_iters=5000 --num_threads=1 --do_profile=true ``` before: ``` 0.789023 ms. 54.8408%. quantized::embedding_bag_4bit_rowwise_offsets (82 nodes) ``` after: ``` 0.620817 ms. 49.7136%. quantized::embedding_bag_4bit_rowwise_offsets (82 nodes) ``` Differential Revision: D26138322 fbshipit-source-id: 0564ed4eaea702f6801f836364dde9419e71a5fb
|
This pull request was exported from Phabricator. Differential Revision: D26138322 |
maratsubkhankulov
force-pushed
the
export-D26138322
branch
from
e2b7112
to
84d3173
Compare
|
This pull request has been merged in 5b0a648. |
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.
Summary: Add out variant for embedding_bag_4bit_rowwise_offsets and add it to static runtime registry
Test Plan: TDB
Differential Revision: D26138322