server : host-memory prompt caching #16391
Draft
+297
−97
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
ggerganov
force-pushed
the
gg/prompt-cache-ext
branch
from
4127199 to
0787f03
Compare
ggerganov
force-pushed
the
gg/prompt-cache-ext
branch
from
0787f03 to
5c0cec4
Compare
This comment was marked as spam.
This comment was marked as spam.
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Outdated suggestions cannot be applied.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.
rel #16117
Initial version of automatic memory offloading to host memory using an extended logic for minimizing the prompt reprocessing. The host-memory prompt cache acts as "extra slots" with which we can calculate prefix similarity and decide to hot-swap them into the
llama_contextif it would reduce the processing.Still WIP, but probably should be useable already.
Note: mtmd workarounds are starting to cause some headaches. For example
server_tokensis not copyable which complicates the cache logic and makes the prompt caching feature incompatible with mtmd.TODOs