crthilakrajandGitHub 7925fa58d9 Fix cuda (#836) ...

* disabled float4 ALU ops for CUDA, small fix to add half_prekernel before kernel_prefix

* added supports_float4_alu option, and disabled for ops_cuda

2023-05-29 07:59:36 -07:00

..

codegen

Fix cuda (#836)

2023-05-29 07:59:36 -07:00

nn

Add MLPerf UNet3D model (#775)

2023-05-28 20:38:19 -07:00

runtime

Fix cuda (#836)

2023-05-29 07:59:36 -07:00

shape

Optimizations in symbolic.py (#796)

2023-05-26 12:59:53 -07:00

graph.py

don't graph consts

2023-04-14 03:32:20 -07:00

helpers.py

int8/uint8 support (#837)

2023-05-28 23:15:06 -07:00

jit.py

jit oops. should add that to commit tests

2023-05-05 22:01:13 -07:00

lazy.py

bugfix for stable diffusion

2023-05-29 00:03:09 +00:00

mlops.py

Add sin/cos/tan (#794)

2023-05-25 09:04:56 -07:00

ops.py

Disktensors! (#819)

2023-05-28 15:40:37 -07:00

tensor.py

Fix conv_transpose2d asymmetric padding (#840)

2023-05-29 07:57:06 -07:00