Add more quantization support for burn-jit

[laggui]

Checklist

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

Changes

Quantization support for burn-jit.

• Completed QJitTensor implementation w/ contained qparams
  • Multiple quantized values are packed into a u32 tensor representation
• Added quantize_per_tensor and dequantize_per_tensor cube kernels
  • Handle affine/symmetric quantization with different vectorization factors based on input tensor size
• Added from_data and into_data conversions
• Added unit tests

Testing

Unit tests.

[codecov]

Codecov Report

Attention: Patch coverage is 60.58520% with 229 lines in your changes missing coverage. Please review.

Project coverage is 85.79%. Comparing base (58ce502) to head (d46076e).
Report is 13 commits behind head on main.

Files with missing lines	Patch %	Lines
...rates/burn-jit/src/kernel/quantization/quantize.rs	44.79%	106 Missing ⚠️
...tes/burn-jit/src/kernel/quantization/dequantize.rs	45.40%	101 Missing ⚠️
crates/burn-jit/src/ops/qtensor.rs	76.66%	21 Missing ⚠️
crates/burn-tensor/src/tensor/data.rs	83.33%	1 Missing ⚠️

Additional details and impacted files

@@            Coverage Diff             @@
##             main    #2275      +/-   ##
==========================================
- Coverage   85.92%   85.79%   -0.13%     
==========================================
  Files         750      754       +4     
  Lines       94328    95189     +861     
==========================================
+ Hits        81047    81671     +624     
- Misses      13281    13518     +237     

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

[laggui]

Had to change the equality assertion for quantized values since some tests produced very close values on macos (in floating point), but the assertion failed on the quantization parameters values.

[nathanielsimard]

LGTM