|
|
fc83d97b41
|
Only support the contiguous case for cublas matmul.
|
2023-06-22 21:39:37 +01:00 |
|
|
|
2231c717d5
|
Fix the matmul example.
|
2023-06-22 21:11:41 +01:00 |
|
|
|
6463d661d8
|
Tweaks.
|
2023-06-22 20:25:14 +01:00 |
|
|
|
aebffcfc13
|
Add a matmul cuda example.
|
2023-06-22 19:44:26 +01:00 |
|
|
|
0671b8c369
|
Improve the gemm config.
|
2023-06-22 19:24:02 +01:00 |
|
|
|
cc78900922
|
Start adding the cublas based matmul.
|
2023-06-22 18:45:10 +01:00 |
|
|
|
683730c21d
|
Add the cublas handle to the cuda device.
|
2023-06-22 18:03:53 +01:00 |
|
|
|
7d9a8ff3f9
|
Do not ignore errors when cloning the storage.
|
2023-06-22 16:29:18 +01:00 |
|
|
|
2f7a072250
|
Rename as_slice to storage_data and implement the cuda version.
|
2023-06-22 16:00:22 +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 |
|
|
|
836ad5f76c
|
Remove one level of indirection for the binary and unary ops.
|
2023-06-22 15:20:51 +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 |
|
|
|
97fe1fac85
|
Add a makefile for cleaning the kernels code.
|
2023-06-22 13:57:51 +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 |
|
|
|
625e08d6ab
|
Abstract the implementation of Shape.
|
2023-06-22 12:39:15 +01:00 |
|
|
|
f052020ba2
|
Support cuda in to_vec3.
|
2023-06-22 12:22:51 +01:00 |
|
|
|
0689d62548
|
Merge pull request #2 from LaurentMazare/matmul
Adding matmul.
|
2023-06-22 13:18:57 +02:00 |
|
|
|
77712d4348
|
Addressing comments.
|
2023-06-22 13:13:35 +02:00 |
|
|
|
449af49b54
|
Adding size checking when creating a tensor from buffer + shape.
|
2023-06-22 13:08:57 +02:00 |
|
|
|
a8b6c848e0
|
Final updates.
|
2023-06-22 12:39:33 +02:00 |
|
|
|
04cf14f35a
|
Moving to gemm and adding matmul backprop.
- Tentative `T` operator.
|
2023-06-22 12:37:02 +02:00 |
|
|
|
9ea220fc6e
|
Fixing tokenizers dep.
|
2023-06-22 12:25:58 +02:00 |
|
|
|
86e4cbbc3d
|
Adding matmul
|
2023-06-22 12:25:58 +02:00 |
|
|
|
ce977b489e
|
Adding matmul?
|
2023-06-22 12:25:58 +02:00 |
|
|
|
87a37b3bf3
|
Retrieve data from the gpu.
|
2023-06-22 11:01:49 +01:00 |
|
|
|
083ced4428
|
Integrate the kernels bits.
|
2023-06-22 09:59:00 +01:00 |
|
|
|
1309932933
|
Polish a bit the kernel loading.
|
2023-06-22 09:16:43 +01:00 |
|
|
|
b5f7553b18
|
Deactivate nightly CI as it's flaky at the moment.
|
2023-06-22 08:36:33 +01:00 |
|
|
|
0a758ffa05
|
Add the fill kernel and use it for 'ones'.
|
2023-06-22 08:33:32 +01:00 |
|
|
|
fc26bab3ed
|
Add some specific errors rather than panicking.
|
2023-06-22 07:51:53 +01:00 |
|
|
|
db35b31050
|
Merge pull request #3 from LaurentMazare/cuda
Add Cuda support.
|
2023-06-21 21:37:54 +01:00 |
|
|
|
7c46de9584
|
Check that the tensor is contiguous before applying the kernel.
|
2023-06-21 21:28:59 +01:00 |
|
|
|
9834151254
|
Small improvement to the cuda panic.
|
2023-06-21 21:25:51 +01:00 |
|
|
|
304a557d84
|
Add a dummy module.
|
2023-06-21 21:16:00 +01:00 |
|
|
|
97d9142dee
|
Add a first kernel.
|
2023-06-21 20:48:22 +01:00 |
|
|
|
fcb4e6b84f
|
Use a reference for the device.
|
2023-06-21 19:55:57 +01:00 |
|
|
|
deb6091099
|
Use a type alias for cuda errors.
|
2023-06-21 19:50:00 +01:00 |
|
|
|
71735c7a02
|
Move the data between the host and the device.
|
2023-06-21 19:43:25 +01:00 |
|
|
|
c654ecdb16
|
Add a specific example for cuda.
|
2023-06-21 18:56:04 +01:00 |
|
|
|
2bfe8f18ab
|
Start adding support for cuda.
|
2023-06-21 18:11:56 +01:00 |
|
|
|
7c317f9611
|
cuda is not available on the CI so deactivate it.
|
2023-06-21 14:50:52 +01:00 |
|
|
|
7adffafeda
|
Abstract the gradient storage.
|
2023-06-21 14:29:48 +01:00 |
|
|
|
68f525f321
|
Move more bits to the backend part.
|
2023-06-21 10:34:51 +01:00 |
|
|
|
eb52b9b343
|
Move the cpu backend specific bits apart.
|
2023-06-21 10:25:56 +01:00 |
|
|
|
b3eb57cd0a
|
Avoid some duplication using a macro + add some basic example to make debugging easier.
|
2023-06-21 10:08:41 +01:00 |
|
|
|
8cde0c5478
|
Add some skeleton code for GPU support.
|
2023-06-21 09:13:57 +01:00 |
|
