|
|
1ad5baecc5
|
Handle transposed matrixes in cublas.
|
2023-06-26 17:49:29 +01:00 |
|
|
|
3761f02aa8
|
Use atomicAdd as a quick workaround some cuda synchronisation issue.
|
2023-06-26 16:31:24 +01:00 |
|
|
|
f2ac5547fc
|
Avoid the race condition on cuda sums.
|
2023-06-26 16:19:06 +01:00 |
|
|
|
cd2a171c06
|
Add the where kernels.
|
2023-06-26 13:25:02 +01:00 |
|
|
|
f6104c4b64
|
Add the reduce-sum kernel.
|
2023-06-26 12:35:26 +01:00 |
|
|
|
16f0f5b9d2
|
Add a cuda kernel for embeddings.
|
2023-06-26 11:47:57 +01:00 |
|
|
|
8ed350dc94
|
Add a couple unitary ops.
|
2023-06-23 20:19:20 +01:00 |
|
|
|
88187b784b
|
Also optimize the contiguous case for the binary cuda kernels.
|
2023-06-23 19:04:13 +01:00 |
|
|
|
5ca309ecb0
|
Optimize the unary cuda kernels for the contiguous case.
|
2023-06-23 18:40:15 +01:00 |
|
|
|
4c8931d2e4
|
More u32 support.
|
2023-06-23 14:54:03 +01:00 |
|
|
|
f8848db001
|
Fix the gelu kernel for f16.
|
2023-06-23 13:38:54 +01:00 |
|
|
|
09b7731b8d
|
Fix unary op.
|
2023-06-23 13:10:26 +02:00 |
|
|
|
56ae71dd4c
|
Address comments.
|
2023-06-23 13:08:04 +02:00 |
|
|
|
fd21c708ab
|
Creating Gelu op (no backward).
|
2023-06-23 13:07:39 +02:00 |
|
|
|
1a90f9d3a6
|
Cuda implementation for copying data around.
|
2023-06-23 11:18:29 +01:00 |
|
|
|
065b7a19c7
|
Stride support for unary ops.
|
2023-06-22 15:46:34 +01:00 |
|
|
|
5b1ab5b687
|
Support strides in affine.
|
2023-06-22 15:38:42 +01:00 |
|
|
|
5276755fb3
|
Add cuda support for unary ops.
|
2023-06-22 15:12:59 +01:00 |
|
|
|
b8f514d9c6
|
Add more binary kernels.
|
2023-06-22 14:07:02 +01:00 |
|
|
|
e1eb86db61
|
Add some first binary op (add).
|
2023-06-22 13:52:02 +01:00 |
|
|
|
83d6198009
|
Simplify the binary kernels.
|
2023-06-22 13:16:03 +01:00 |
|
|
|
4b1c3405e9
|
Add a couple cuda kernels from dfdx.
|
2023-06-22 12:56:29 +01:00 |
|
|
|
083ced4428
|
Integrate the kernels bits.
|
2023-06-22 09:59:00 +01:00 |
|
