Paged attention transformation #24177
Closed
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
github-actions
bot
added
category: Core
Contributor
There was a problem hiding this comment.
we typically name files with snake_case
Contributor
There was a problem hiding this comment.
should we create paged_attention subfolder to contain files related to this new meta-transformation?
CuriousPanCake
commented
Apr 24, 2024
src/common/transformations/src/transformations/common_optimizations/StateManagementPattern.cpp
Outdated
Show resolved
Hide resolved
CuriousPanCake
commented
Apr 24, 2024
src/common/transformations/src/transformations/common_optimizations/StateManagementPattern.cpp
Outdated
Show resolved
Hide resolved
CuriousPanCake
commented
Apr 24, 2024
src/common/transformations/src/transformations/common_optimizations/StateManagementPattern.cpp
Show resolved
Hide resolved
CuriousPanCake
commented
Apr 24, 2024
src/common/transformations/src/transformations/common_optimizations/StateManagementPattern.cpp
Show resolved
Hide resolved
CuriousPanCake
commented
Apr 24, 2024
src/common/transformations/src/transformations/common_optimizations/StateManagementPattern.cpp
Show resolved
Hide resolved
CuriousPanCake
commented
Apr 24, 2024
src/common/transformations/src/transformations/common_optimizations/StateManagementPattern.cpp
Outdated
Show resolved
Hide resolved
CuriousPanCake
commented
Apr 24, 2024
src/common/transformations/src/transformations/common_optimizations/StateManagementPattern.cpp
Outdated
Show resolved
Hide resolved
CuriousPanCake
force-pushed
the
paged_attention_transformation
branch
from
64d760d to
5efd778
Compare
CuriousPanCake
commented
Apr 24, 2024
src/common/transformations/src/transformations/common_optimizations/StateManagementPattern.cpp
Outdated
Show resolved
Hide resolved
CuriousPanCake
commented
Apr 24, 2024
src/common/transformations/src/transformations/common_optimizations/StateManagementPattern.cpp
Outdated
Show resolved
Hide resolved
CuriousPanCake
commented
Apr 24, 2024
src/common/transformations/src/transformations/common_optimizations/StateManagementPattern.cpp
Outdated
Show resolved
Hide resolved
CuriousPanCake
commented
Apr 24, 2024
src/common/transformations/src/transformations/common_optimizations/StateManagementPattern.cpp
Outdated
Show resolved
Hide resolved
slyalin
reviewed
Apr 24, 2024
itikhono
reviewed
Apr 24, 2024
itikhono
reviewed
Apr 24, 2024
slyalin
reviewed
Apr 25, 2024
CuriousPanCake
force-pushed
the
paged_attention_transformation
branch
from
8dd42df to
9a665e7
Compare
CuriousPanCake
force-pushed
the
paged_attention_transformation
branch
from
9a665e7 to
d6730d9
Compare
.../transformations/include/transformations/common_optimizations/TotalSequenceLengthPattern.hpp
Show resolved
Hide resolved
itikhono
reviewed
May 1, 2024
...n/transformations/include/transformations/common_optimizations/PrevSequenceLengthPattern.hpp
Show resolved
Hide resolved
ilya-lavrenov
approved these changes
May 1, 2024
Contributor
ilya-lavrenov
left a comment
ilya-lavrenov
left a comment
There was a problem hiding this comment.
opt125m and llama2 work
this list of models work I will re-open this PR and resolve some comments |
15 tasks
|
a new PR has been opened: #24336 |
ilya-lavrenov
pushed a commit
that referenced
this pull request
May 2, 2024
### Details: Ported SDPA to PagedAttention transformation from python to C++ code. the related PRs: #24127 #24177 Tested model scope: - [x] "hf-internal-testing/tiny-random-BloomForCausalLM", - [x] "hf-internal-testing/tiny-random-FalconForCausalLM", - [x] "hf-internal-testing/tiny-random-Starcoder2ForCausalLM", - [x] "hf-internal-testing/tiny-random-GPTJForCausalLM", - [x] "hf-internal-testing/tiny-random-StableLmForCausalLM", - [x] "hf-internal-testing/tiny-random-LlamaForCausalLM", - [x] "hf-internal-testing/tiny-random-MistralForCausalLM", - [x] "hf-internal-testing/tiny-random-OPTForCausalLM", - [x] "hf-internal-testing/tiny-random-PhiForCausalLM", - [x] "hf-internal-testing/tiny-random-StableLmForCausalLM", - [x] "facebook/opt-125m", - [x] "llama2", - [x] "bigcode/starcoder2-7b" - [ ] "mosaicml/mpt-7b-chat" (FAILED both py/c++) - acceptable for this PR Issue: RuntimeError: Check '(axis_range_min <= axis) && (axis <= axis_range_max)' failed at src/core/src/validation_util.cpp:386: Concat Parameter axis 2 out of the tensor rank range [0, 0]. - [x] _means, that the response to the dedicated prompt is the same for the py and c++ transformations._ ### Tickets: - *CVS-138664* --------- Co-authored-by: Sergey Lyalin <[email protected]> Co-authored-by: Andrii Staikov <[email protected]>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 participants
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.
wip: added the setup part and half of the first matcher