chenyu 97b05f567e revert the .detach() in layernorm (#4904) ...

* revert the .detach() in layernorm

it's only correct in LayerNorm where input is the data, and not correct in GroupNorm and InstanceNorm that reused layernorm.
Added backward tests for weights, bias and input for these norms.

* bigger atol for llvm

* relax backward more

2024-06-10 18:02:05 -04:00

..

external

amd support kernel with bf16 (#4863)

2024-06-08 22:52:32 +03:00

imported

change Tensor.stack to method (#4719)

2024-05-24 17:04:19 -04:00

models

skip a few clang test that took > 30 seconds in CI (#4126)

2024-04-10 02:00:34 -04:00

testextra

process replay in all of CI (#4884)

2024-06-10 14:49:29 -04:00

unit

test uop as symbolic (#4870)

2024-06-09 12:15:11 +02:00

web

fast path for copy (#2548)

2023-12-01 11:34:47 -08:00

__init__.py

All devices are equal! (#196)

2020-12-15 23:44:08 -08:00

Dockerfile

Docker fix (#1039)

2023-06-25 10:38:58 -07:00

helpers.py

retire hsa (#4885)

2024-06-09 11:33:03 +03:00

test_arange.py

apply NOOPT in test_arange complexity (#4774)

2024-05-29 23:12:35 -04:00

test_assign.py

test masked assign views (#4599)

2024-05-15 15:06:48 +03:00

test_const_folding.py

lazy folding: mul -1 is neg, and neg neg is noop (#4472)

2024-05-08 01:52:22 -04:00

test_conv_shapetracker.py

ScheduleItem uses Buffer (#3995)

2024-03-29 20:50:27 -07:00

test_conv.py

add back "CPU" in test_onnx_backend supports_device (#3426)

2024-02-16 00:49:30 -05:00

test_copy_speed.py

remove cpu and torch backends (#3399)

2024-02-15 16:55:39 +01:00

test_custom_function.py

all realize 2 (#4527)

2024-05-10 22:43:09 -07:00

test_device_speed.py

add renderer class (#4524)

2024-05-10 21:40:02 -07:00

test_dtype_alu.py

retire hsa (#4885)

2024-06-09 11:33:03 +03:00

test_dtype.py

configure derandomizing CI tests (#4793)

2024-05-31 17:06:58 +03:00

test_fusion_op.py

process replay in all of CI (#4884)

2024-06-10 14:49:29 -04:00

test_fuzz_shape_ops.py

configure derandomizing CI tests (#4793)

2024-05-31 17:06:58 +03:00

test_gc.py

threefry again (#3785)

2024-03-18 16:47:07 -04:00

test_image_dtype.py

move image into tensor.py. delete features (#4603)

2024-05-15 10:50:25 -07:00

test_jit.py

retire hsa (#4885)

2024-06-09 11:33:03 +03:00

test_kernel_cache.py

move the compiler cache to be global (#2957)

2024-01-01 10:59:56 -08:00

test_lazybuffer.py

test for LazyBuffer._view when mask out and degrade into const (#4465)

2024-05-07 12:56:23 -04:00

test_lazyop.py

split to schedule.py (#3949)

2024-03-26 21:02:46 -07:00

test_linearizer_failures.py

example kernel that triggers Memory access fault for resnet on red (#4678)

2024-05-21 18:59:36 -04:00

test_linearizer_overflows.py

move graph/search to engine (#4596)

2024-05-14 23:12:59 -07:00

test_linearizer.py

Multireduce atomic local load/store test (#4786)

2024-06-05 14:41:19 +03:00

test_masked_st.py

multitensor start (#2676)

2023-12-07 17:07:05 -08:00

test_method_cache.py

simple LoadOps.ASSIGN (#3745)

2024-03-14 20:44:34 -07:00

test_multitensor.py

test cases for multitensor adds const (#4892)

2024-06-08 22:57:48 -04:00

test_net_speed.py

nv mockgpu (#4600)

2024-05-15 23:46:08 +03:00

test_nn.py

revert the .detach() in layernorm (#4904)

2024-06-10 18:02:05 -04:00

test_ops.py

test case for Tensor.var reducing over size = 1 axis (#4902)

2024-06-10 12:11:39 -04:00

test_optim.py

nv mockgpu (#4600)

2024-05-15 23:46:08 +03:00

test_pattern_matcher.py

cosmetic changes to uop _match (#4897)

2024-06-09 18:29:42 -04:00

test_pickle.py

hotfix: pickle jit works if you delete the function

2024-05-05 10:14:03 -07:00

test_randomness.py

configure derandomizing CI tests (#4793)

2024-05-31 17:06:58 +03:00

test_sample.py

enable test_sample for all backend (#2593)

2023-12-03 17:20:27 -05:00

test_schedule.py

compile raise CompileError and skip only RuntimeError in multiprocess… (#4646)

2024-05-19 00:25:25 -04:00

test_search.py

process replay in all of CI (#4884)

2024-06-10 14:49:29 -04:00

test_setitem.py

setitem in-place operator tests (#4577)

2024-05-14 01:28:02 -04:00

test_specific_conv.py

nv mockgpu (#4600)

2024-05-15 23:46:08 +03:00

test_speed_v_torch.py

nv mockgpu (#4600)

2024-05-15 23:46:08 +03:00

test_subbuffer.py

support view in nv/amd (#4812)

2024-06-03 22:11:52 +03:00

test_symbolic_jit.py

support symbolic reshape with non-contiguous (#4844)

2024-06-05 16:01:19 -04:00

test_symbolic_ops.py

symbolic Tensor.var (#4843)

2024-06-05 12:55:54 -04:00

test_symbolic_shapetracker.py

support symbolic reshape with non-contiguous (#4844)

2024-06-05 16:01:19 -04:00

test_tensor_data.py

tolist to return multidimensional list (#4192)

2024-04-18 07:43:10 +04:00

test_tensor_variable.py

symbolic Tensor.var (#4843)

2024-06-05 12:55:54 -04:00

test_tensor.py

canonicalize 0 in shape in View.create (#4815)

2024-06-03 13:37:37 -04:00

test_to_numpy.py

Apply ruff linting rules to tests (#2473)

2023-11-27 21:24:06 -08:00

test_tqdm.py

tqdm replacement (#4846)

2024-06-09 23:46:03 +02:00

test_uop_graph.py

CMPEQ -> CMPNE and make it safe to pad (#4818)

2024-06-03 18:02:15 -04:00

test_uops_stats.py

Fix flop coutning for mulacc (#4640)

2024-05-20 12:06:00 -04:00

test_uops.py

UOps.IF* to graph spec (#4894)

2024-06-09 07:00:12 -04:00

test_winograd.py

new uops is an actual graph (#4560)

2024-05-17 18:00:18 -07:00

test_zero_copy.py

remove numpy from device (#3123)

2024-01-14 19:36:05 -08:00