This repository has been archived by the owner on Oct 25, 2024. It is now read-only.
[LLM Runtime] Optmized dropout operator #707
Merged
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
XinyuYe-Intel
approved these changes
Nov 17, 2023
airMeng
reviewed
Nov 17, 2023
intel_extension_for_transformers/llm/operator/csrc/include/dropout.hpp
Outdated
Show resolved
Hide resolved
airMeng
reviewed
Nov 17, 2023
airMeng
approved these changes
Nov 17, 2023
Signed-off-by: Wenxin Zhang <wenxin.zhang@intel.com>
|
there is something wrong when build binary, please check @zhewang1-intc |
airMeng
reviewed
Nov 20, 2023
intel_extension_for_transformers/llm/operator/csrc/src/dropout.cpp
Outdated
Show resolved
Hide resolved
zhenwei-intel
added a commit
that referenced
this pull request
Nov 21, 2023
This reverts commit 7d276cd.
sywangyi
pushed a commit
that referenced
this pull request
Nov 21, 2023
* pass ut on avx2/avx512 * add relative tests * fix gcc11 compile Signed-off-by: Wenxin Zhang <wenxin.zhang@intel.com>
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
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Outdated suggestions cannot be applied.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.
Type of Change
feature or bug fix or documentation or others: feature
API changed or not: Yes
user can call optimized fwd/bwd dropout operator in QBits, 3X+ perf improvement compared to pytorch.
e.g.
Description
detail description
JIRA ticket: https://jira.devtools.intel.com/browse/NLPTOOLKIU-958
optmized fwd/bwd dropout operator under AVX512/AVX2 ISA, including a high-performance rand-generator.
change QBits log from cout to torch::LOG.
Expected Behavior & Potential Risk
the expected behavior that triggered by this PR
How has this PR been tested?
how to reproduce the test (including hardware information)
tested on 335T(spr) & desktop(Core i9-10900)
Dependency Change?
any library dependency introduced or removed
No.