Commit Graph

2322 Commits

Author SHA1 Message Date
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
f319583530 More QOL changes, binary op for constants. 2023-06-21 08:59:08 +01:00
0839954770 Add some binary ops. 2023-06-21 08:32:35 +01:00
3a5405ca6d Move the StridedIndex in its own module. 2023-06-21 07:44:36 +01:00
23db8a7da8 Simplify the test. 2023-06-21 07:33:42 +01:00
78bac0ed32 Add a couple operators. 2023-06-20 22:32:11 +01:00
f1f372b13e Add the affine transformation. 2023-06-20 21:51:35 +01:00
e04d0ac1ac Cosmetic change to the backprop test. 2023-06-20 20:56:50 +01:00
a419a9da72 Add some backprop test. 2023-06-20 20:54:35 +01:00