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

feat(model): support new models #457

Merged
merged 1 commit into from
Mar 28, 2024
Merged

feat(model): support new models #457

merged 1 commit into from
Mar 28, 2024

Conversation

tonywang10101
Copy link
Contributor

@tonywang10101 tonywang10101 commented Mar 24, 2024 •
edited
Loading

Because

  • in model-backend 0.12.0, we are going to utilize 4 A100 40G GPU

This commit

  • update model config based on the following strategy

GPU1:
yolov7
mobilenetv2
yolov7-stomata
llava 13b (needs 26G VRAM)

GPU 2:
stable-diffusion-xl (needs 16G VRAM)
controlnet-canny (needs 16G VRAM)

GPU 3:
llama2-7b (needs 16G VRAM)
llama2-7b-chat (needs 16G VRAM)

GPU 4:
llamacode 7b (needs 16G VRAM)
zephyr-7b (needs 16G VRAM)

@heiruwu heiruwu changed the title feat(model): support new models for ver 0.12.0 feat(model): support new models Mar 25, 2024
heiruwu
heiruwu approved these changes Mar 25, 2024
View reviewed changes
Copy link
Member

@heiruwu heiruwu left a comment

Choose a reason for hiding this comment

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

LGTM

@donch1989 donch1989 merged commit 7e311d5 into main Mar 28, 2024
46 checks passed
@donch1989 donch1989 deleted the support_new_models_0.12.0 branch March 28, 2024 09:36
@droplet-bot droplet-bot mentioned this pull request Mar 28, 2024
Merged
@tonywang10101 tonywang10101 restored the support_new_models_0.12.0 branch March 28, 2024 15:31
donch1989 pushed a commit that referenced this pull request Apr 2, 2024
@droplet-bot
chore(main): release 0.27.0-beta (#450)
14b332b 
🤖 I have created a release *beep* *boop*
---


##
[0.27.0-beta](v0.26.1-beta...v0.27.0-beta)
(2024-04-02)


### Features

* **helm,docker-compose:** add registry service
([#435](#435))
([8f56582](8f56582))
* **helm:** add configuration for read-replica database
([#455](#455))
([ba80559](ba80559))
* **model:** support new models
([#457](#457))
([7e311d5](7e311d5))


### Bug Fixes

* **cicd:** fix uploading console tests artifact issue
([#463](#463))
([78b001d](78b001d))


### Miscellaneous Chores

* release v0.27.0-beta
([c0c331a](c0c331a))

---
This PR was generated with [Release
Please](https://github.com/googleapis/release-please). See
[documentation](https://github.com/googleapis/release-please#release-please).
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@heiruwu heiruwu heiruwu approved these changes

@donch1989 donch1989 Awaiting requested review from donch1989 donch1989 is a code owner

@jvallesm jvallesm Awaiting requested review from jvallesm jvallesm is a code owner

@Sarthak-instill Sarthak-instill Awaiting requested review from Sarthak-instill Sarthak-instill is a code owner

Assignees
No one assigned
Labels
core
Projects
No open projects
🔮 Instill Core
Status: 👋 Done
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
4 participants
@tonywang10101 @heiruwu @donch1989 @droplet-bot