Thanks to visit codestin.com
Credit goes to github.com

Skip to content
This repository was archived by the owner on Jun 3, 2025. It is now read-only.

[Text Generation] Enable internal kv cache if CPU architecture is avx512#1122

Merged
dbogunowicz merged 5 commits into
mainfrom
feature/damian/text_generation_avx2512
Jul 18, 2023
Merged

[Text Generation] Enable internal kv cache if CPU architecture is avx512#1122
dbogunowicz merged 5 commits into
mainfrom
feature/damian/text_generation_avx2512

Conversation

@dbogunowicz

@dbogunowicz dbogunowicz commented Jul 17, 2023

Copy link
Copy Markdown
Contributor

If the CPU does not support avx512, disable internal kv cache.

@dbogunowicz dbogunowicz changed the title [Text Generation] Enable internal kv cache if CPU architecture is avx2512 [Text Generation] Enable internal kv cache if CPU architecture is avx512 Jul 17, 2023
SageMoore
SageMoore previously approved these changes Jul 17, 2023
Comment thread src/deepsparse/transformers/pipelines/text_generation.py Outdated
bfineran
bfineran previously approved these changes Jul 17, 2023
rahul-tuli
rahul-tuli previously approved these changes Jul 17, 2023
@dbogunowicz dbogunowicz merged commit 745ecc3 into main Jul 18, 2023
@dbogunowicz dbogunowicz deleted the feature/damian/text_generation_avx2512 branch July 18, 2023 13:42
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

5 participants