George Hotz e0201922e3 Q network for pruning BEAM / uops deduping / BEAM_ESTIMATE (#2142) ...

* stable diffusion < 324ms

* revert swap action

* fix tests due to more sum splitting

* REDUCEOP_SPLIT_THRESHOLD env var

* added from unaligned np test (#2134)

* align cpu buffer before copy into cl buffer (#2135)

* remove shelve from handcode_resnet50_opt.py (#2139)

* Add dictionary keys to reduce db size (#2131)

* work

* ignore beam cache

* dictionary keys are generic

* minor db cleanups

* fix baseline and extract dataset

* fix training

* log likelihood

* more lin to feats

* sts

* training policynet

* net sort of works

* dedup

* refactor, stupid new actions

* fix uops deduping

* BEAM_ESTIMATE

---------

Co-authored-by: chenyu <chenyu@fastmail.com>
Co-authored-by: imaolo <56898718+imaolo@users.noreply.github.com>

2023-10-27 10:53:06 -10:00

..

mlperf

op logger + replay (#2021)

2023-10-08 15:10:18 -07:00

sovits_helpers

Implementation of SoftVC VITS SVC model (#1371)

2023-08-13 19:43:23 -07:00

vgg7_helpers

waifu2x vgg7: testcase, auto-RGBA->RGB, function to grab pretrained models, training "fix" (#2117)

2023-10-19 22:07:15 -07:00

__init__.py

failing llama test

2023-03-11 16:28:10 -08:00

benchmark_train_efficientnet.py

add cache collector (#1595)

2023-08-28 19:59:55 -07:00

compile_efficientnet.py

Allow multi-input model export (#1995)

2023-10-07 04:13:34 -07:00

compile_tensorflow.py

moved extras/jit.py -> tinygrad/jit.py (#599)

2023-02-25 08:32:33 -08:00

efficientnet.py

Fix plt output comment (#1428)

2023-08-03 23:35:52 -07:00

gpt2.py

beam=16 makes gpt2 gpu-time < 5ms on 3090 (#2154)

2023-10-27 10:21:27 -10:00

handcode_resnet50_opt.py

Q network for pruning BEAM / uops deduping / BEAM_ESTIMATE (#2142)

2023-10-27 10:53:06 -10:00

hlb_cifar10.py

hip multigpu training (#1878)

2023-10-24 17:35:53 -04:00

index.html

simple exporting models (#1344)

2023-08-01 09:35:48 -07:00

llama.py

Fix llama json loading (#2160)

2023-10-27 10:21:56 -10:00

mask_rcnn.py

MaskRCNN Inference (#884)

2023-06-25 15:37:51 -07:00

mnist_gan.py

move state to nn/state (#1619)

2023-08-22 07:36:24 -07:00

serious_mnist.py

move state to nn/state (#1619)

2023-08-22 07:36:24 -07:00

simple_conv_bn.py

with Tensor.train() (#1935)

2023-09-28 18:02:31 -07:00

so_vits_svc.py

use class Foo: instead of class Foo(): (#1797)

2023-09-06 12:20:25 -07:00

stable_diffusion.py

universal disk cache (#2130)

2023-10-22 10:56:57 -07:00

train_efficientnet.py

Fix examples/train_efficientnet (#1947)

2023-10-02 02:23:38 -07:00

train_resnet.py

move state to nn/state (#1619)

2023-08-22 07:36:24 -07:00

transformer.py

move state to nn/state (#1619)

2023-08-22 07:36:24 -07:00

vgg7.py

waifu2x vgg7: testcase, auto-RGBA->RGB, function to grab pretrained models, training "fix" (#2117)

2023-10-19 22:07:15 -07:00

vit.py

.cpu().numpy() -> .numpy() (#1594)

2023-08-21 09:53:29 -07:00

vits.py

[ready] Replacing os with pathlib (#1708)

2023-08-30 10:41:08 -07:00

whisper.py

whisper: make file transcription work, add basic CI test (#2042)

2023-10-13 17:13:35 -07:00

yolov3.py

.cpu().numpy() -> .numpy() (#1594)

2023-08-21 09:53:29 -07:00

yolov8-onnx.py

[ready] Replacing os with pathlib (#1708)

2023-08-30 10:41:08 -07:00

yolov8.py

use class Foo: instead of class Foo(): (#1797)

2023-09-06 12:20:25 -07:00