Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

[KV Cache Injection] MPT #1691

Merged
merged 1 commit into from
Sep 13, 2023
Merged

[KV Cache Injection] MPT #1691

merged 1 commit into from
Sep 13, 2023

Conversation

dbogunowicz
Copy link
Contributor

No description provided.

@dbogunowicz dbogunowicz marked this pull request as ready for review July 28, 2023 08:18
dbogunowicz
dbogunowicz commented Jul 28, 2023
View reviewed changes
src/sparseml/exporters/transforms/kv_cache/configs.py Outdated
)


def get_kv_cache_config(
model_path: str,
supported_configs: List[BaseModel] = [OPT_CONFIG, CODEGEN_CONFIG, BLOOM_CONFIG],
Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

We need to remove BLOOM, we are not supporting it officially in the nightly.

Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

if we have some internal testing, hidden support seems ok

@dbogunowicz dbogunowicz changed the base branch from main to delete-orphaned-nodes July 31, 2023 09:00
Base automatically changed from delete-orphaned-nodes to main July 31, 2023 19:40
bfineran
bfineran reviewed Aug 1, 2023
View reviewed changes
src/sparseml/exporters/transforms/kv_cache/configs.py Outdated
)


def get_kv_cache_config(
model_path: str,
supported_configs: List[BaseModel] = [OPT_CONFIG, CODEGEN_CONFIG, BLOOM_CONFIG],
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

if we have some internal testing, hidden support seems ok

src/sparseml/exporters/transforms/kv_cache/transforms_base.py Outdated Show resolved Hide resolved
mgoin
mgoin reviewed Aug 14, 2023
View reviewed changes
Copy link
Member

@mgoin mgoin left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

FYI I've tested this with MPT instruct, chat, and replit code to much success

@mgoin mgoin merged commit 56d0c92 into main Sep 13, 2023
8 of 11 checks passed
@mgoin mgoin deleted the feature/damian/mpt branch September 13, 2023 15:43
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@mgoin mgoin mgoin approved these changes

@bfineran bfineran bfineran approved these changes

Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.

None yet
3 participants
@dbogunowicz @mgoin @bfineran