enable internal kv bucket in llama#11
Closed
xt574chen wants to merge 0 commit into
Closed
Conversation
xt574chen
requested review from
bhargaveede,
libinta and
vivekgoe
as code owners
|
@dvarshney-habana @MrGeva since changes are related to Llama inference, please review. |
ghost
approved these changes
Jan 31, 2024
bhargaveede
force-pushed
the
habana-main
branch
2 times, most recently
from
9730605 to
c1154b2
Compare
|
huggingface#658 - please check my latest comments in actual PR. |
Author
|
@puneeshkhanna thank you for the comments. This branch has conflicts with the latest main. Please review this feature in another PR #24. |
astachowiczhabana
pushed a commit
that referenced
this pull request
Nov 20, 2024
* [SW-204303] Enable Fp8 flow with INC for sdxl in OH Change-Id: I5bf82613200b4a1dd08882c3731dab57d28992cd
sushildubey171
added a commit
that referenced
this pull request
Nov 22, 2024
Change-Id: I5bf82613200b4a1dd08882c3731dab57d28992cd
xinyu-intel
pushed a commit
that referenced
this pull request
Mar 4, 2025
* [SW-204303] Enable Fp8 flow with INC for sdxl in OH Change-Id: I5bf82613200b4a1dd08882c3731dab57d28992cd
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What does this PR do?
To enhance throughput in scenarios with long new tokens, break down the KV cache into multiples of the bucket width. Use this to compute attention rather than using the entire KV cache. Add
--bucket_size=128 --bucket_internalto the commands to enable the feature.