int8 dynamic prefill weight only decode #1436
Merged
Conversation
This file contains 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
Summary: This PR adds in a sparsity option to the LLaMa benchmarks. Test Plan: Reviewers: Subscribers: Tasks: Tags:
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/ao/1436
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit b144a53 with merge base 567cb46 ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
drisspg
approved these changes
Dec 30, 2024
amdfaa
pushed a commit
that referenced
this pull request
Jan 10, 2025
This PR adds in weight_only_decode option to int8_dynamic_activation_int8_weight, which when set will use dynamic quantization for matmuls of shape (> 1, x) * (x, n) and weight only quantization for the batch_size=1 case. It also updates generate.py to take in a text file for the prompt, we use this to demonstrate these prefill speedups with sh demo_summarize.sh.
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Outdated suggestions cannot be applied.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.
This PR adds in weight_only_decode option to
int8_dynamic_activation_int8_weight, which when set will use dynamic quantization for matmuls of shape (> 1, x) * (x, n) and weight only quantization for the batch_size=1 case.It also updates
generate.pyto take in a text file for the prompt, we use this to demonstrate these prefill speedups withsh demo_summarize.sh.