Skip to content

[quant] Use Int8DynActInt4WeightQuantizer in torchao #2551

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.

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

Closed
wants to merge 7 commits into from

Conversation

jerryzh168
Copy link
Contributor

@jerryzh168 jerryzh168 commented Mar 21, 2024

Stack from ghstack (oldest at bottom):

Summary:
att

Test Plan:
python3 -m examples.models.llama2.export_llama -c stories110M.pt -p params.json -qmode 8da4w -X -d fp32

Reviewers:

Subscribers:

Tasks:

Tags:

Summary:
att

Test Plan:
python3 -m examples.models.llama2.export_llama -c stories110M.pt -p params.json -qmode 8da4w -X -d fp32

Reviewers:

Subscribers:

Tasks:

Tags:

[ghstack-poisoned]
Copy link

pytorch-bot bot commented Mar 21, 2024

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/2551

Note: Links to docs will display an error until the docs builds have been completed.

❌ 2 New Failures, 1 Unrelated Failure

As of commit c061495 with merge base 6bef9e7 (image):

NEW FAILURES - The following jobs have failed:

BROKEN TRUNK - The following job failed but were present on the merge base:

👉 Rebase onto the `viable/strict` branch to avoid these failures

This comment was automatically generated by Dr. CI and updates every 15 minutes.

jerryzh168 added a commit that referenced this pull request Mar 21, 2024
Summary:
att

Test Plan:
python3 -m examples.models.llama2.export_llama -c stories110M.pt -p params.json -qmode 8da4w -X -d fp32

Reviewers:

Subscribers:

Tasks:

Tags:

ghstack-source-id: 2fc1355
Pull Request resolved: #2551
@facebook-github-bot facebook-github-bot added the CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. label Mar 21, 2024
@jerryzh168 jerryzh168 requested a review from kimishpatel March 21, 2024 00:36
…` in torchao"

Summary:
att

Test Plan:
python3 -m examples.models.llama2.export_llama -c stories110M.pt -p params.json -qmode 8da4w -X -d fp32

Reviewers:

Subscribers:

Tasks:

Tags:

[ghstack-poisoned]
Summary:
att

Test Plan:
python3 -m examples.models.llama2.export_llama -c stories110M.pt -p params.json -qmode 8da4w -X -d fp32

Reviewers:

Subscribers:

Tasks:

Tags:

[ghstack-poisoned]
jerryzh168 added a commit that referenced this pull request Mar 21, 2024
Summary:
att

Test Plan:
python3 -m examples.models.llama2.export_llama -c stories110M.pt -p params.json -qmode 8da4w -X -d fp32

Reviewers:

Subscribers:

Tasks:

Tags:

ghstack-source-id: a8eba1d
Pull Request resolved: #2551
@jerryzh168 jerryzh168 changed the base branch from gh/jerryzh168/5/base to main March 21, 2024 23:11
@facebook-github-bot
Copy link
Contributor

@jerryzh168 has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator.

@jerryzh168 jerryzh168 changed the base branch from main to gh/jerryzh168/5/orig March 22, 2024 01:41
…` in torchao"

Summary:
att

Test Plan:
python3 -m examples.models.llama2.export_llama -c stories110M.pt -p params.json -qmode 8da4w -X -d fp32

Reviewers:

Subscribers:

Tasks:

Tags:

[ghstack-poisoned]
Summary:
att

Test Plan:
python3 -m examples.models.llama2.export_llama -c stories110M.pt -p params.json -qmode 8da4w -X -d fp32

Reviewers:

Subscribers:

Tasks:

Tags:

[ghstack-poisoned]
jerryzh168 added a commit that referenced this pull request Mar 22, 2024
Summary:
att

Test Plan:
python3 -m examples.models.llama2.export_llama -c stories110M.pt -p params.json -qmode 8da4w -X -d fp32

Reviewers:

Subscribers:

Tasks:

Tags:

ghstack-source-id: b66176d
Pull Request resolved: #2551
@jerryzh168 jerryzh168 force-pushed the gh/jerryzh168/5/orig branch from 3c40571 to aaee570 Compare March 22, 2024 01:41
@jerryzh168 jerryzh168 changed the base branch from gh/jerryzh168/5/orig to main March 22, 2024 01:41
@jerryzh168 jerryzh168 changed the base branch from main to gh/jerryzh168/5/orig March 22, 2024 01:56
…` in torchao"

Summary:
att

Test Plan:
python3 -m examples.models.llama2.export_llama -c stories110M.pt -p params.json -qmode 8da4w -X -d fp32

Reviewers:

Subscribers:

Tasks:

Tags:

[ghstack-poisoned]
Summary:
att

Test Plan:
python3 -m examples.models.llama2.export_llama -c stories110M.pt -p params.json -qmode 8da4w -X -d fp32

Reviewers:

Subscribers:

Tasks:

Tags:

[ghstack-poisoned]
jerryzh168 added a commit that referenced this pull request Mar 22, 2024
Summary:
att

Test Plan:
python3 -m examples.models.llama2.export_llama -c stories110M.pt -p params.json -qmode 8da4w -X -d fp32

Reviewers:

Subscribers:

Tasks:

Tags:

ghstack-source-id: 76e1516
Pull Request resolved: #2551
@jerryzh168 jerryzh168 force-pushed the gh/jerryzh168/5/orig branch from aaee570 to f401505 Compare March 22, 2024 01:56
@jerryzh168 jerryzh168 changed the base branch from gh/jerryzh168/5/orig to main March 22, 2024 03:05
@facebook-github-bot
Copy link
Contributor

@jerryzh168 has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator.

@facebook-github-bot
Copy link
Contributor

@jerryzh168 merged this pull request in a6aefc0.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. Merged
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants