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.

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

Refactor jit quantized tensor representation #2604

Merged
merged 17 commits into from
Dec 13, 2024
Merged

Conversation

laggui
Copy link
Member

@laggui laggui commented Dec 9, 2024

Checklist

  • Confirmed that run-checks all script has been executed.

Related Issues/PRs

On the way to burn-fusion quantize

Follow-up to #2479

Changes

  • Simplified quantized tensor handle repr (one handle per qtensor)
  • Removed strategy from QTensorPrimitive trait
  • Refactored burn-jit quantized tensor repr and kernel
    • Removed QJitTensor (use JitTensor with QFloat dtype)
    • Refactored cube kernels w/ stored quantization params in cube tensor and new

Testing

Unit tests

Copy link

codecov bot commented Dec 9, 2024

Codecov Report

Attention: Patch coverage is 50.00000% with 206 lines in your changes missing coverage. Please review.

Project coverage is 81.90%. Comparing base (ebd7649) to head (a93e8da).
Report is 3 commits behind head on main.

Files with missing lines Patch % Lines
...rates/burn-jit/src/kernel/quantization/quantize.rs 33.94% 72 Missing ⚠️
...tes/burn-jit/src/kernel/quantization/dequantize.rs 44.44% 45 Missing ⚠️
crates/burn-jit/src/kernel/quantization/qtensor.rs 4.34% 22 Missing ⚠️
crates/burn-tch/src/tensor.rs 0.00% 10 Missing ⚠️
crates/burn-fusion/src/server.rs 25.00% 9 Missing ⚠️
crates/burn-jit/src/tensor/base.rs 62.50% 9 Missing ⚠️
crates/burn-fusion/src/tensor.rs 75.86% 7 Missing ⚠️
crates/burn-fusion/src/client/mutex.rs 53.84% 6 Missing ⚠️
crates/burn-fusion/src/ops/qtensor.rs 77.27% 5 Missing ⚠️
crates/burn-ndarray/src/backend.rs 0.00% 5 Missing ⚠️
... and 8 more
Additional details and impacted files
@@            Coverage Diff             @@
##             main    #2604      +/-   ##
==========================================
+ Coverage   81.86%   81.90%   +0.04%     
==========================================
  Files         832      831       -1     
  Lines      106399   106121     -278     
==========================================
- Hits        87099    86920     -179     
+ Misses      19300    19201      -99     

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

@laggui laggui marked this pull request as ready for review December 9, 2024 15:41
@laggui laggui merged commit 0dd228c into main Dec 13, 2024
11 checks passed
@laggui laggui deleted the refactor/jit/qtensor branch December 13, 2024 20:24
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants