add an example for quantizing LLaMa 4 Scout #3408
Merged
+221
−0
Conversation
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
Contributor
Author
|
Stack from ghstack (oldest at bottom): |
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/ao/3408
Note: Links to docs will display an error until the docs builds have been completed. This comment was automatically generated by Dr. CI and updates every 15 minutes. |
vkuzo
added a commit
that referenced
this pull request
Dec 1, 2025
Summary: Adds an e2e example of how to use torchao to quantize LLaMa 4 Scout. Note that this needs: * a recent `transformers` version (higher than 4.57, not officially released yet so user needs to build from source) * a recent `fbgemm_gpu` version nightly from `2025.11.22` or after * to run this in vLLM, vllm-project/vllm#28421 is needed (not yet landed). Test Plan: ```bash with-proxy time python examples/quantize_llama_4.py ~/local/tmp/20251201_test/ ``` Reviewers: Subscribers: Tasks: Tags: ghstack-source-id: 3c47130 ghstack-comment-id: 3599037297 Pull-Request: #3408
meta-cla
bot
added
the
CLA Signed
vkuzo
added
the
topic: documentation
jcaip
reviewed
Dec 1, 2025
jerryzh168
approved these changes
Dec 1, 2025
vkuzo
added a commit
that referenced
this pull request
Dec 2, 2025
Summary: Adds an e2e example of how to use torchao to quantize LLaMa 4 Scout. Note that this needs: * a recent `transformers` version (higher than 4.57, not officially released yet so user needs to build from source) * a recent `fbgemm_gpu` version nightly from `2025.11.22` or after * to run this in vLLM, vllm-project/vllm#28421 is needed (not yet landed). Test Plan: ```bash with-proxy time python examples/quantize_llama_4.py ~/local/tmp/20251201_test/ ``` Reviewers: Subscribers: Tasks: Tags: ghstack-source-id: 76125e9 ghstack-comment-id: 3599037297 Pull-Request: #3408
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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.
Summary:
Adds an e2e example of how to use torchao to quantize LLaMa 4 Scout.
Note that this needs:
transformersversion (higher than 4.57, not officiallyreleased yet so user needs to build from source)
fbgemm_gpuversion nightly from2025.11.22or afteris needed (not yet landed).
Test Plan:
Reviewers:
Subscribers:
Tasks:
Tags: