George Hotz fce432d2e3 Ops.FUSE makes softmax a single kernel (#9808) ...

* KERNELIZE makes softmax a single kernel

* single kernel works

* softmax works

* broken

* correct

* skip that test

* kernelize tests

* rename to fuse

* better reduce_push_add_ones code

* correct now

* cleanups

* oops

* return None if we can't push ones

* rename + docs

* atol fixes group

* flash attention broken test

2025-04-09 22:56:28 +08:00

..

external

single kernel softmax (#9776)

2025-04-08 12:35:48 +08:00

imported

CLANG -> CPU (#9189)

2025-02-20 18:03:09 -05:00

mockgpu

Refactor ops_amd.py (MI300X prereq) (#9428)

2025-03-29 00:17:20 +07:00

models

add onnx frontend stub [pr] (#9558)

2025-03-24 12:24:34 +08:00

testextra

CLANG -> CPU (#9189)

2025-02-20 18:03:09 -05:00

unit

multi stage graph_rewrite_map (#9803)

2025-04-09 15:59:45 +08:00

web

Move efficientnet example (#8087)

2024-12-06 15:48:16 +01:00

__init__.py

All devices are equal! (#196)

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

Dockerfile

new cloud is cloudy [pr] (#7631)

2024-11-11 20:18:04 +08:00

helpers.py

add name uop (#9149)

2025-02-18 15:26:58 +08:00

test_amd_llvm.py

add amd llvm compiler (#9519)

2025-03-21 23:13:27 +08:00

test_arange.py

use Ops.REDUCE (#9721)

2025-04-04 10:14:34 +08:00

test_assign.py

KERNEL op try 3 (#9061)

2025-02-17 14:47:54 +01:00

test_compile_failures.py

enable a few tests that work now (#7721)

2024-11-15 14:30:52 -05:00

test_const_folding.py

is_realized only if buffer is allocated (#9253)

2025-02-26 08:58:08 +01:00

test_conv_shapetracker.py

remove inputs+outputs attributes from ScheduleItem [pr] (#9192)

2025-02-21 13:48:11 +01:00

test_conv.py

db in wal mode (#5388)

2024-07-12 20:43:36 -07:00

test_copy_speed.py

CLANG -> CPU (#9189)

2025-02-20 18:03:09 -05:00

test_device_speed.py

add name uop (#9149)

2025-02-18 15:26:58 +08:00

test_dtype_alu.py

Revert "FP8 support on NVIDIA (#8631)"

2025-04-09 12:27:41 +08:00

test_dtype.py

Revert "FP8 support on NVIDIA (#8631)"

2025-04-09 12:27:41 +08:00

test_fusion_op.py

just schedule in test_recursive_pad [pr] (#8860)

2025-02-02 15:01:24 +02:00

test_fuzz_shape_ops.py

CLANG -> CPU (#9189)

2025-02-20 18:03:09 -05:00

test_gc.py

move Buffer refcount increment out of schedule.py (#9564)

2025-03-25 12:08:27 +08:00

test_graph.py

minor test cleanups (#9770)

2025-04-07 15:29:12 +03:00

test_hcq.py

minor test cleanups (#9770)

2025-04-07 15:29:12 +03:00

test_image_dtype.py

VALIDATE_WITH_CPU [pr] (#9488)

2025-03-18 15:15:04 +08:00

test_interop.py

hotfix: interop example (#9237)

2025-02-25 10:32:00 +03:00

test_jit.py

jit: prune independent copies (#9749)

2025-04-05 20:50:28 +03:00

test_kernel_cache.py

CLANG -> CPU (#9189)

2025-02-20 18:03:09 -05:00

test_linearizer_dumb.py

tc_select noop (#8801)

2025-01-29 13:53:23 -05:00

test_linearizer_failures.py

linearizer failure test for OUT OF BOUNDS ACCESS (#9738)

2025-04-04 03:48:43 -04:00

test_linearizer_overflows.py

move time_linearizer to extra.optimization.helpers [pr] (#9048)

2025-02-12 15:49:58 -05:00

test_linearizer.py

Revert "FP8 support on NVIDIA (#8631)"

2025-04-09 12:27:41 +08:00

test_masked_st.py

multitensor start (#2676)

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

test_memory_planner.py

add memplanner tests (#9577)

2025-03-26 10:59:39 +07:00

test_metal.py

Use MTLCompiler directly (v2) (#7920)

2024-12-04 16:36:48 +08:00

test_method_cache.py

simple LoadOps.ASSIGN (#3745)

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

test_multitensor.py

skip CI CPU test_data_parallel_resnet_train_step (#9685)

2025-04-02 01:04:54 -04:00

test_net_speed.py

hotfix: test_net_speed can't backward before realize

2024-12-19 20:32:59 -08:00

test_nn.py

update embedding test to not use dtypes.long [pr] (#9556)

2025-03-23 21:33:38 -04:00

test_ocl.py

Fix GPT2 with OpenCL backend. (#6821)

2024-10-01 16:57:22 +08:00

test_ops.py

Revert "FP8 support on NVIDIA (#8631)"

2025-04-09 12:27:41 +08:00

test_optim.py

raise RuntimeError in schedule_step if not Tensor.training [pr] (#8834)

2025-01-31 12:03:04 -05:00

test_pickle.py

fix UPat.location after pickle (#9763)

2025-04-07 15:16:42 +08:00

test_profiler.py

metal: fix transfer profiling (#8659)

2025-01-17 23:47:01 +03:00

test_quantize_onnx.py

add onnx frontend stub [pr] (#9558)

2025-03-24 12:24:34 +08:00

test_randomness.py

Revert "FP8 support on NVIDIA (#8631)"

2025-04-09 12:27:41 +08:00

test_rearrange_einops.py

Missing features from rearrange (#6184)

2024-08-19 11:19:07 -07:00

test_renderer_failures.py

increase test tolerance (#9719)

2025-04-03 15:24:09 +08:00

test_rewrite_tracked_childen.py

split into grouper.py (#9768)

2025-04-07 18:40:59 +08:00

test_sample.py

enable more webgpu tests (#9502)

2025-03-18 23:03:54 -04:00

test_schedule.py

move view_left to grouper.py + tiny reorders [pr] (#9780)

2025-04-08 15:39:28 +08:00

test_search.py

acc_dtype -> dtype (#9402)

2025-03-10 16:05:30 -04:00

test_setitem.py

delete forced_realize (#8615)

2025-01-20 09:40:36 -08:00

test_softmax_fusion.py

Ops.FUSE makes softmax a single kernel (#9808)

2025-04-09 22:56:28 +08:00

test_specific_conv.py

Solve get_grouped_dims does not split issue (#9085)

2025-02-16 19:57:29 -05:00

test_speed_v_torch.py

hotfix: cat tests 2048 instead of 256

2025-04-03 10:37:56 +08:00

test_subbuffer.py

remove contiguous in test_subbuffer_used [pr] (#9046)

2025-02-12 14:41:16 -05:00

test_symbolic_jit.py

UOp.variable (#7010)

2024-10-12 18:20:44 +08:00

test_symbolic_ops.py

few minor code cleanups [pr] (#8267)

2024-12-15 23:44:51 -05:00

test_symbolic_shapetracker.py

update test_merge_view_recursion_err2 [pr] (#8339)

2024-12-19 18:29:34 -05:00

test_tensor_data.py

[BUGFIX] Tensor([]).data() (#7884)

2024-11-24 16:42:57 -05:00

test_tensor_uop.py

remove const_arg (#9002)

2025-02-10 12:45:11 +01:00

test_tensor_variable.py

combine pad2d with pad (#7677)

2024-11-14 17:56:02 +08:00

test_tensor.py

add test for checking const gradients (#9598)

2025-03-27 15:17:37 -04:00

test_tiny.py

Ops.FUSE makes softmax a single kernel (#9808)

2025-04-09 22:56:28 +08:00

test_to_numpy.py

Apply ruff linting rules to tests (#2473)

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

test_transcendental.py

Fix DSP transcendentals (#9542)

2025-03-22 11:08:18 +08:00

test_uop_graph.py

add validation of the bounds of Ops.INDEX (#9503)

2025-03-20 12:15:55 +08:00

test_uops_stats.py

use Ops.REDUCE (#9721)

2025-04-04 10:14:34 +08:00

test_uops.py

fast idiv (#9755)

2025-04-07 08:32:24 -04:00

test_winograd.py

create_schedule([x.lazydata]) -> x.schedule() in tests (#8449)

2024-12-31 03:15:52 +08:00

test_zero_copy.py

CLANG -> CPU (#9189)

2025-02-20 18:03:09 -05:00