Files
candle/candle-core/tests
Laurent Mazare eb26e2467e Add the cuda dequantize f16 kernels. (#2137)
* Add the cuda dequantize f16 kernels.

* Expose the cuda kernels.

* Add some testing + fix.

* Test the other cases too.

* A few more tests.

* Add an environment variable to enable the dequantize f16 + matmul behavior.
2024-04-28 20:05:05 +02:00
..
2024-04-28 08:18:04 +02:00