Abstract out sharable interface of Dram KV wrapper #5057
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
✅ Deploy Preview for pytorch-fbgemm-docs ready!
To edit notification comments on pull requests, go to your Netlify project configuration. |
|
@tomlintbl has exported this pull request. If you are a Meta employee, you can view the originating Diff in D85162982. |
Summary: - We need an elegant way to dynamically swap registration of KV implementation. - A solution is to abstract the current KV wrappers and make them inherit the same interface. - The original DramKVWrapper is the bridge of Python and C++ code. By delegating the actual functionality through a impl_ member, which has the type of the aforementioned interface, we can keep the registration as is but swap out detailed impl_ at runtime. V2: - Move set_dram_kv and get_dram_kv into IKVEmbeddingInference - Add lazy-initialization in DramImpl::init - Add TORCH_CHECK to throw when impl is not set before accessing - Rename IKVEmbeddingInference to KVEmbeddingInferenceInterface Differential Revision: D85162982
tomlintbl
force-pushed
the
export-D85162982
branch
from
9acf74f to
467870b
Compare
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.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:
V2:
Differential Revision: D85162982