Implement fast VLA attention with Triton and update benchmarks#10
Merged
Conversation
Author: @Akshay594 Add a new fast VLA attention module implementing sequential, parallel (prefix-scan) and an optional Triton-fused variant (src/models/attention/fast_vla.py). Include parallel-scan and Sherman–Morrison scan implementations, KV-explosion fixes, and Triton kernel guarded by HAS_TRITON. Add a basic unit test for the parallel variant (tests/test_fast_vla.py) and a speed benchmark script (scripts/benchmark_speed.py). Update plotting script (scripts/plot_retrieval.py) to aggregate retrieval CSVs and produce a combined accuracy plot. Scripts save figures under results/ and handle CPU/GPU/Triton availability.
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Author: @Akshay594