George Hotz fff1f046b0 Simple version of the new GPU backend (#458) ... * newgpu * more to delete * hmm, tests pass with constant folding * fix lint/type * fix constant folding * comment and rerun tests * lazy touchups * fix graph_batchnorm test * smaller transformer to fix OOM * Revert "smaller transformer to fix OOM" This reverts commit a44ef8edc2. * no func cache * introspect * touchups * CLASTKernel * ugh, it was lru_cache * codegen * spacing * old gpu still in opencl * typing fix		2023-01-10 19:16:02 -08:00
..
efficientnet	add ViT test and car	2022-06-05 17:12:43 -07:00
__init__.py	All devices are equal! (#196)	2020-12-15 23:44:08 -08:00
Dockerfile	testdocker	2023-01-09 12:41:52 -08:00
external_test_llvm.py	LLVM Backend take 2 (#403)	2022-10-26 20:32:31 -07:00
external_test_opt.py	one more opt test	2022-10-28 18:37:53 -07:00
graph_batchnorm.py	Simple version of the new GPU backend (#458)	2023-01-10 19:16:02 -08:00
test_cl_tiler.py	hasattr and DeviceBuffer type fixups	2022-10-28 09:05:45 -07:00
test_conv.py	Fold reduce (#362)	2022-07-19 09:24:02 -07:00
test_efficientnet.py	test_onnx works with enet also	2022-06-11 14:30:26 -07:00
test_gc.py	set requires_grad to None (#387)	2022-09-21 11:16:02 -04:00
test_mnist.py	Fix weight init: this work? (#391)	2022-09-25 16:46:33 -04:00
test_net_speed.py	import tests from CL metal texture fix	2022-09-19 20:01:47 -04:00
test_nn.py	ugh, why did that fail	2022-10-01 13:38:43 -04:00
test_onnx.py	support float16 onnx weights (#384)	2022-09-15 09:12:18 -04:00
test_ops.py	shapetracker from newgpu (#456)	2023-01-09 12:40:01 -08:00
test_optim.py	tinygrad.nn (#367)	2022-08-18 07:41:00 -07:00
test_shapetracker.py	shapetracker from newgpu (#456)	2023-01-09 12:40:01 -08:00
test_speed_v_torch.py	shapetracker from newgpu (#456)	2023-01-09 12:40:01 -08:00
test_tensor.py	set requires_grad to None (#387)	2022-09-21 11:16:02 -04:00
test_train.py	Simple version of the new GPU backend (#458)	2023-01-10 19:16:02 -08:00