George Hotz c5bd28e21d start work on schedule cache (#13529) ...

* start work on schedule cache

* local unique

* schedule cache works

* schedule cache cleanup

* fix tests

* preserve metadata

* oops, fix cache

* put that there

* fix spec

* always miss

* why is that broken?

* src[0].op

* fix process replay

* delete abstractions2

* reenable the actual schedule cache

* metadata is best effort

* fix JIT in examples/gradaccum_mnist.py

* full jit

* fixed and test is real

2025-12-04 17:24:49 -08:00

..

device

fix a few tests [pr] (#13498)

2025-11-29 13:43:45 -08:00

external

start work on schedule cache (#13529)

2025-12-04 17:24:49 -08:00

mockgpu

nv: minimal hevc (#13502)

2025-11-30 16:46:55 +03:00

models

tighter test_real_world mem and kernel count bounds (#13573)

2025-12-04 13:35:39 -05:00

opt

require renderer argument in get_program, removes device opening in process replay [pr] (#13524)

2025-12-03 02:05:31 +08:00

speed

ops_gpu -> ops_cl (#12103)

2025-09-10 15:15:48 -04:00

testextra

add needs_second_gpu decorator (#13543)

2025-12-02 19:08:23 -08:00

unit

start work on schedule cache (#13529)

2025-12-04 17:24:49 -08:00

web

time viz (#10763)

2025-06-17 19:39:34 +03:00

__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 needs_second_gpu decorator (#13543)

2025-12-02 19:08:23 -08:00

test_arange.py

require renderer argument in get_program, removes device opening in process replay [pr] (#13524)

2025-12-03 02:05:31 +08:00

test_assign.py

remove assign contiguous hack (#12659)

2025-10-14 16:42:14 +08:00

test_compile_failures.py

Mesa NIR backend (NAK/LLVMpipe) (#12089)

2025-10-15 17:38:33 +08:00

test_const_folding.py

shared_codegen_spec and fix index spec (#12967)

2025-10-29 09:14:11 +01:00

test_custom_kernel.py

fix: add test_sum_int and remove outdated TODO in test_custom_kernel (#13560)

2025-12-03 21:51:58 -05:00

test_dtype_alu.py

add loads at the end (#12988)

2025-10-30 10:42:19 +08:00

test_dtype.py

Mesa NIR backend (NAK/LLVMpipe) (#12089)

2025-10-15 17:38:33 +08:00

test_edgecases.py

Mesa NIR backend (NAK/LLVMpipe) (#12089)

2025-10-15 17:38:33 +08:00

test_fusion_op.py

Cleanup const buffers (#12829)

2025-10-21 14:53:49 +02:00

test_gc.py

fix a few tests [pr] (#13498)

2025-11-29 13:43:45 -08:00

test_graph.py

add needs_second_gpu decorator (#13543)

2025-12-02 19:08:23 -08:00

test_image_dtype.py

Cleanup const buffers (#12829)

2025-10-21 14:53:49 +02:00

test_interop.py

hotfix: interop example (#9237)

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

test_jit_cases.py

enumerate cases of Tensors in the JIT (#10548)

2025-05-28 11:51:27 -07:00

test_jit.py

add needs_second_gpu decorator (#13543)

2025-12-02 19:08:23 -08:00

test_kernel_cache.py

make method_cache account for compiler (#12156)

2025-09-13 17:00:11 +03:00

test_linearizer_dumb.py

add loads at the end (#12988)

2025-10-30 10:42:19 +08:00

test_linearizer_failures.py

require renderer argument in get_program, removes device opening in process replay [pr] (#13524)

2025-12-03 02:05:31 +08:00

test_linearizer.py

fix cifar while keeping openpilot fused (#13528)

2025-12-02 12:05:56 -08:00

test_memory_planner.py

memplan: fix large buffers planning (#11878)

2025-08-27 23:54:27 +03:00

test_method_cache.py

make method_cache account for compiler (#12156)

2025-09-13 17:00:11 +03:00

test_multitensor.py

add needs_second_gpu decorator (#13543)

2025-12-02 19:08:23 -08:00

test_nn.py

fix and test loading num_batches_tracked (#13538)

2025-12-04 01:22:49 -08:00

test_ops.py

match torch clamp backward (#13533)

2025-12-02 17:58:32 -05:00

test_opt_gemm.py

require renderer argument in get_program, removes device opening in process replay [pr] (#13524)

2025-12-03 02:05:31 +08:00

test_optim.py

use torch 2.9 and its Muon in test (#12773)

2025-10-21 13:35:17 -04:00

test_opts.py

require renderer argument in get_program, removes device opening in process replay [pr] (#13524)

2025-12-03 02:05:31 +08:00

test_outerworld_range.py

remove dtype from range, it will be dtypes.index soon [pr] (#11914)

2025-08-29 09:52:07 -07:00

test_outerworld.py

vmap on full model (#13340)

2025-11-18 16:06:06 -08:00

test_pickle.py

no sym in pm_reduce [pr] (#13398)

2025-11-20 16:49:09 -05:00

test_profiler.py

test_graph is flaky

2025-11-26 16:37:42 -08:00

test_quantize_onnx.py

require renderer argument in get_program, removes device opening in process replay [pr] (#13524)

2025-12-03 02:05:31 +08:00

test_randomness.py

add needs_second_gpu decorator (#13543)

2025-12-02 19:08:23 -08:00

test_rangeify.py

fix indexing bug with convs

2025-11-07 16:45:19 -08:00

test_remote.py

skip more multi remote tests (#12410)

2025-10-02 04:50:46 +03:00

test_renderer_failures.py

add loads at the end (#12988)

2025-10-30 10:42:19 +08:00

test_schedule.py

add SGD to beautiful_mnist (#13571)

2025-12-04 12:17:29 -05:00

test_setitem.py

remove UOp.st (#12716)

2025-10-16 14:44:09 +08:00

test_softmax_fusion.py

fuse hasn't worked since rangeify, remove it (#13057)

2025-11-02 14:01:52 +08:00

test_stunning.py

remove FUSE_ARANGE (#12511)

2025-10-08 04:54:07 -04:00

test_subbuffer.py

add needs_second_gpu decorator (#13543)

2025-12-02 19:08:23 -08:00

test_symbolic_jit.py

remove trivial use of RANGEIFY flag (#12550)

2025-10-09 02:29:38 -04:00

test_symbolic_ops.py

update test_conv2d_ceildiv_edge_case (#12779)

2025-10-18 16:43:32 -04:00

test_tensor_uop.py

new linearizer with early endrange (#12823)

2025-10-21 17:37:48 +08:00

test_tensor_variable.py

remove UOp.st (#12716)

2025-10-16 14:44:09 +08:00

test_tensor.py

start work on schedule cache (#13529)

2025-12-04 17:24:49 -08:00

test_tiny.py

beautiful SQTT_PARSE=1 with color (#13428)

2025-11-23 01:05:14 -08:00

test_to_numpy.py

Apply ruff linting rules to tests (#2473)

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

test_transcendental.py

Mesa NIR backend (NAK/LLVMpipe) (#12089)

2025-10-15 17:38:33 +08:00

test_uop_graph.py

fix after end (#13542)

2025-12-02 18:42:58 -08:00

test_uops_stats.py

require renderer argument in get_program, removes device opening in process replay [pr] (#13524)

2025-12-03 02:05:31 +08:00

test_uops.py

Update tests (#13479)

2025-11-28 18:35:28 -08:00

test_zero_copy.py

unify cpu and llvm (#11982)

2025-09-09 13:54:44 +03:00