rfcs: add proposal for indirect KV cache support #1894
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
igorsafo
force-pushed
the
igorsafo/rfcs/indirect-kv-cache
branch
6 times, most recently
from
3496d5c
to
49965e6
Compare
igorsafo
force-pushed
the
igorsafo/rfcs/indirect-kv-cache
branch
from
49965e6
to
4579bf2
Compare
rongzha1
reviewed
May 11, 2024
| that is responsible for the influence of the context on the output token. | ||
|
|
||
| Here is the diagram: | ||
|  |
There was a problem hiding this comment.
in this pattern graph, out shape of BMM(N, T) seems be (N, H, T, T) not (N, H, 1, T) ?
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Outdated suggestions cannot be applied.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.
Description
A link to the document: link
RFC PR