Commit Graph

1095 Commits

Author SHA1 Message Date
George Hotz
3728ef6d02 better alphas 2022-09-05 16:48:26 -07:00
George Hotz
0fda854b3e other prompt example 2022-09-05 16:14:16 -07:00
George Hotz
16cb4290c4 cat horse winning 2022-09-05 16:05:14 -07:00
George Hotz
1043fa067a it renders something 2022-09-05 15:52:14 -07:00
George Hotz
5a685b93ac brown img 2022-09-05 15:20:18 -07:00
George Hotz
98d6264987 all models match 2022-09-05 12:27:54 -07:00
George Hotz
b8bd34b5d2 fix last bug in unet probz 2022-09-05 11:32:44 -07:00
George Hotz
3df67aa0af fix transformer bugs 2022-09-05 11:26:32 -07:00
George Hotz
2ed3bb6223 clip model is running 2022-09-05 11:26:32 -07:00
Ollin Boer Bohan
2c6f4e4c66 Make creation helpers use fp32 by default (#374)
* Make creation helpers use fp32 by default

half the big = twice the fast

* Fix flake8 with an extra multiply
2022-09-04 13:47:27 -07:00
George Hotz
1a54ea2417 runs on torch cpu 2022-09-04 12:06:42 -07:00
George Hotz
9590d92750 stable diffusion compiles (add no_init) 2022-09-04 11:40:50 -07:00
George Hotz
172683c314 work 2022-09-04 11:21:09 -07:00
George Hotz
bcb867cdd6 better idea for numbers, do the division in python 2022-09-03 16:23:39 -07:00
George Hotz
39e1d23c88 from_number_like to fix div issue 2022-09-03 16:19:16 -07:00
George Hotz
c2a030fe55 one liner that's more clear 2022-09-03 16:08:48 -07:00
George Hotz
4a3ed58edb more readable actually 2022-09-03 16:00:35 -07:00
George Hotz
633f31dc73 easier to read 2022-09-03 15:53:58 -07:00
George Hotz
6578e08919 cleanups for Mid 2022-09-03 15:50:33 -07:00
George Hotz
852de7c66c remove ugly parens 2022-09-03 15:41:37 -07:00
George Hotz
6b190c2fa5 stable diffusion works 2022-09-03 13:55:36 -07:00
George Hotz
871b2a7b52 fix check 2022-09-03 13:37:40 -07:00
George Hotz
947e10dab0 yolo 2022-09-03 12:39:48 -07:00
George Hotz
033a3ecccf found tinygrad bug 2022-09-03 12:32:43 -07:00
George Hotz
114728d363 torch bs 2022-09-03 11:57:23 -07:00
George Hotz
356732515b stable_diffusion: add attn and layernorm 2022-09-03 11:02:27 -07:00
George Hotz
4dadd95e3c fix tests hopefully, more stable diffusion 2022-09-03 10:38:31 -07:00
George Hotz
c01a8c5c2d stable diffusion start 2022-09-03 10:08:42 -07:00
Comma Device
c07bf72d6e save free 200ms 2022-08-31 20:31:42 -04:00
George Hotz
2e9b7637b3 don't save input buffers 2022-08-31 15:37:38 -07:00
George Hotz
a3fc64a585 fix batchnorm folding in openpilot compile 2022-08-31 13:04:49 -07:00
Comma Device
a734df98fa TEST_ENET for openpilot compiler 2022-08-31 13:23:36 -04:00
George Hotz
d919ac32af fix wrong size input 2022-08-31 09:07:34 -07:00
George Hotz
040640a580 fix cl import error 2022-08-31 08:43:44 -07:00
George Hotz
e194ae0c1d typos 2022-08-30 19:52:21 -07:00
Mitchell Goff
3af650b028 Rewrote Tensor.cat to be shorter and (hopefully) clearer (#372)
* Rewrote Tensor.cat to be shorter and (hopefully) clearer

* Use cumsum[-1] instead of separate sum
2022-08-30 16:15:07 -07:00
George Hotz
db56297011 line count 2022-08-30 15:23:35 -07:00
George Hotz
33ac355bcd still broken 2022-08-29 19:08:07 -07:00
George Hotz
5efab7cf1d add reciprocal 2022-08-29 18:00:24 -07:00
George Hotz
880707f2d2 no torch test if no torch 2022-08-29 15:29:19 -07:00
George Hotz
5eba228844 print inputs 2022-08-29 08:56:04 -07:00
George Hotz
fa33ba716e flip that 2022-08-28 11:27:33 -07:00
George Hotz
dd587d26e3 oops, compare with abs 2022-08-28 11:23:21 -07:00
George Hotz
dc7af8c3ac thneed run float32 2022-08-28 11:03:35 -07:00
Comma Device
f0d11f29c7 float32 in image desc 2022-08-28 08:47:43 -07:00
Comma Device
9678cb8a1a hmm, the native exp/log breaks it too much 2022-08-22 17:13:08 -07:00
Comma Device
0c1378e7db native_exp is way faster on qcom 2022-08-22 16:58:50 -07:00
George Hotz
2162cd3383 fix typing 2022-08-22 16:25:15 -07:00
Comma Device
e0a8d0f836 image input works 2022-08-22 16:04:17 -07:00
George Hotz
18340e7d30 remove from_image 2022-08-22 15:52:26 -07:00