leopf b6d9b276bb GGUF support (#7046) ...

* basic loader, untested

* testing

* remove utils import in test

* q8_0

* q4_1

* end to end testing

* minor cleanup

* fix casting

* moved to state

* move tests

* move dequant to fn

* fix lint elif

* remove gguf from extra

* fix dict union

* q6_k simpler

* naming and spacing

* gpt2-gguf example

* cleanup

* move gguf example

* minor cleanup

---------

Co-authored-by: George Hotz <72895+geohot@users.noreply.github.com>

2024-10-21 16:15:34 +08:00

..

external

don't throw in fuzz_linearizer (#7148)

2024-10-18 09:28:30 -04:00

imported

node cleanup + local metal test speed [pr] (#6880)

2024-10-04 18:14:23 +08:00

models

UOp.variable (#7010)

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

testextra

names shadowing builtins (#5179)

2024-06-27 08:15:01 -04:00

unit

GGUF support (#7046)

2024-10-21 16:15:34 +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

No pyint again (#7156)

2024-10-19 13:48:59 -04:00

test_arange.py

default threefry (#6116)

2024-09-25 17:45:13 +08:00

test_assign.py

RUF018 assignment-in-assert [run_process_replay] (#6172)

2024-08-19 00:34:52 -04:00

test_compile_failures.py

CIFAR trainer + various bugfixes / improvements (#6146)

2024-08-20 16:58:46 -07:00

test_const_folding.py

lazy const fold idiv 1 (#6285)

2024-08-26 10:29:59 -04:00

test_conv_shapetracker.py

remove expr_idxs [run_process_replay] (#6567)

2024-09-17 18:34:51 +08:00

test_conv.py

db in wal mode (#5388)

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

test_copy_speed.py

node cleanup + local metal test speed [pr] (#6880)

2024-10-04 18:14:23 +08:00

test_device_speed.py

remove iter from uopgraph (#6110)

2024-08-16 15:58:29 -07:00

test_dtype_alu.py

skip test_bfloat16_unary on AMD (#7169)

2024-10-21 01:00:47 +03:00

test_dtype.py

No pyint again (#7156)

2024-10-19 13:48:59 -04:00

test_fusion_op.py

delete seen from the scheduler api [run_process_replay] (#6427)

2024-09-09 16:26:34 +08:00

test_fuzz_shape_ops.py

fix typing for test to run in py38 (#4930)

2024-06-12 13:22:30 -04:00

test_gc.py

seed in tensor (#6869)

2024-10-06 14:46:58 -04:00

test_graph.py

fix hcq sync (#5062)

2024-06-26 17:50:37 +03:00

test_hcq.py

move hcq device to runtime [pr] (#6879)

2024-10-04 22:26:50 +08:00

test_image_dtype.py

add copyin copyout for image on GPU [run_process_replay] (#6580)

2024-09-18 16:06:20 +08:00

test_jit.py

seed in tensor (#6869)

2024-10-06 14:46:58 -04:00

test_kernel_cache.py

move the compiler cache to be global (#2957)

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

test_lazybuffer.py

move lazy to engine [pr] (#6886)

2024-10-04 23:19:26 +08:00

test_linearizer_dumb.py

minor dtype cleanup [pr] (#7124)

2024-10-17 17:41:23 +08:00

test_linearizer_failures.py

No pyint again (#7156)

2024-10-19 13:48:59 -04:00

test_linearizer_overflows.py

minor dtype cleanup [pr] (#7124)

2024-10-17 17:41:23 +08:00

test_linearizer.py

PtrDType is dataclass [pr] (#7125)

2024-10-18 09:40:33 -04:00

test_masked_st.py

multitensor start (#2676)

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

test_metal.py

Metal with CDLL instead of py-objc (#6545)

2024-09-25 17:43:01 +08:00

test_method_cache.py

simple LoadOps.ASSIGN (#3745)

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

test_multitensor.py

uop resolve [run_process_replay] (#6826)

2024-10-01 13:11:42 +08:00

test_net_speed.py

nv mockgpu (#4600)

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

test_nn.py

fix all test warnings (#7024)

2024-10-18 08:56:40 +08:00

test_ocl.py

Fix GPT2 with OpenCL backend. (#6821)

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

test_ops.py

remove bitcast backward in function.py (#7031)

2024-10-13 10:08:27 -04:00

test_optim.py

improve test_dropout_on_shard (#4912)

2024-06-11 11:36:02 -04:00

test_pickle.py

cloud device [pr] (#6964)

2024-10-11 12:24:06 +08:00

test_profiler.py

remove pyint [pr] (#7016)

2024-10-12 22:36:24 +08:00

test_randomness.py

seed in tensor (#6869)

2024-10-06 14:46:58 -04:00

test_rearrange_einops.py

Missing features from rearrange (#6184)

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

test_renderer_failures.py

minor dtype cleanup [pr] (#7124)

2024-10-17 17:41:23 +08:00

test_sample.py

UOp.variable (#7010)

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

test_schedule.py

track_rewrites by function call [pr] (#7165)

2024-10-20 17:45:25 +03:00

test_search.py

minor dtype cleanup [pr] (#7124)

2024-10-17 17:41:23 +08:00

test_setitem.py

skip TestSetitem.test_setitem_inplace_operator (#7103)

2024-10-16 18:59:08 +03:00

test_specific_conv.py

nv mockgpu (#4600)

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

test_speed_v_torch.py

remove CUDACPU flag in tests [run_process_replay] (#5902)

2024-08-04 16:06:38 -04:00

test_subbuffer.py

move lazy to engine [pr] (#6886)

2024-10-04 23:19:26 +08:00

test_symbolic_jit.py

UOp.variable (#7010)

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

test_symbolic_ops.py

UOp.variable (#7010)

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

test_symbolic_shapetracker.py

remove NumNode (#7035)

2024-10-13 16:42:19 -04:00

test_tensor_data.py

BEAM_COMPARE=2 validates the correctness of BEAM kernels (#5458)

2024-07-13 13:53:43 -07:00

test_tensor_variable.py

node cleanup + local metal test speed [pr] (#6880)

2024-10-04 18:14:23 +08:00

test_tensor.py

fix all test warnings (#7024)

2024-10-18 08:56:40 +08:00

test_tiny.py

hotfix: add test_tiny, because many times it's what you want

2024-10-14 16:32:33 +08:00

test_to_numpy.py

Apply ruff linting rules to tests (#2473)

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

test_transcendental.py

Suppress warnings in transcendental tests. (#6891)

2024-10-05 07:37:17 +08:00

test_uop_graph.py

minor dtype cleanup [pr] (#7124)

2024-10-17 17:41:23 +08:00

test_uops_stats.py

minor dtype cleanup [pr] (#7124)

2024-10-17 17:41:23 +08:00

test_uops.py

scheduler ast rewrite reorders from big graph [pr] (#7168)

2024-10-21 00:47:58 +03:00

test_viz.py

track_rewrites by function call [pr] (#7165)

2024-10-20 17:45:25 +03:00

test_winograd.py

merge uops with ops (#6111)

2024-08-16 18:17:57 -04:00

test_zero_copy.py

remove numpy from device (#3123)

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