github/tinygrad
1
1
Fork 0
mirror of https://github.com/tinygrad/tinygrad.git synced 2026-01-10 07:28:15 -05:00
Code Issues Packages Projects Releases Wiki Activity
3,153 Commits 203 Branches 13 Tags
637879af788516ef447be65a2b619ddab4e886e6
Commit Graph

3153 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
George Hotz
637879af78 add direct install to readme 2023-12-19 18:04:00 -08:00
chenyu
ad233d557f disable reshape merging with masks (#2858) 
fuzzer found a bug, and it's not complete
 2023-12-19 19:06:16 -05:00
chenyu
1231ec5a02 run the sz.py line count at the end of linter ci (#2857) 2023-12-19 16:33:12 -05:00
George Hotz
ac6ec936cd update contributing 2023-12-19 12:19:14 -08:00
George Hotz
e477cc2f45 hotfix: README is ~25 ops to stop getting PRs about it 2023-12-19 11:53:35 -08:00
Oleg Rybalko
42a038c83f More readable torch_load ext check (#2853) 
* more readable extension check

* enable tarfile test

* detach tensor if requires grad in torch
 2023-12-19 14:53:15 -05:00
chenyu
172a88e719 skip slow test_indexing on METAL (#2852) 
LLVM still runs and is a lot faster, would be curious to know why.
also reworded some error messages and remove regex check
 2023-12-19 12:00:54 -05:00
chenyu
6d7e9e0a56 hotfix convert Y_train to int before passing into index (#2850) 2023-12-19 11:40:56 -05:00
geohotstan
fec8e9060c Add simple fancy indexing exceptions (#2706) 
* fancy indexing raise error

* updated error message

* improved error check

* oops

* fixed onnx

* oops typo

* merge

* add full_flatten

* try

* merged and updated some tests

* more cleaning

* done

* temp fix onnx

* try

* add todo in onnx_test

* reword

* gah
 2023-12-19 11:23:51 -05:00
qazal
417d42a363 UOps support for ImageDType (#2848) 
* cleanup buffer dtypes in global_load

* update with feedback
 2023-12-19 09:39:48 -05:00
George Hotz
90fb09b55c remove unused _device_extra_args 2023-12-18 22:14:58 -08:00
George Hotz
b2192b5400 minor improvements (#2845) 2023-12-18 22:09:08 -08:00
George Hotz
d086325b1b hotfix: failing tests 2023-12-18 21:12:42 -08:00
George Hotz
07df14aa0e HIP cleanups (#2843) 
* move everything to code_for_op to reason about it

* loop the loopable parts

* its not that unreadable

* these are loopable too

* nitpick

* tests p1 - replace these with the actual compiler running alu ops tests

* tests p2: compile test_dtype_alu in HIP!

+add to CI

* nobody liked test_renderer

* revert test_dtypes change

* isolated mockhip tests

* dont need the WHERE hack after #2782

+ruff

* bf16 is broken in HIP

job failed in: https://github.com/tinygrad/tinygrad/actions/runs/7232101987/job/19705951290?pr=2778#step:8:73

* picking this back up

* add compile tests for unary ops and binary ops

* MOD is only in ints

* CMPLT wont work after the dtypes pr is merged because it will always be bool

* test all combinations

* Update cstyle.py

* don't use vload

* no getenv

* set seed

---------

Co-authored-by: qazal <qazal.software@gmail.com>
Co-authored-by: qazal <77887910+Qazalin@users.noreply.github.com>
 2023-12-18 21:09:32 -08:00
George Hotz
b6d71b131e hotfix: push broken tests 2023-12-18 21:08:42 -08:00
George Hotz
9b35186bbe hotfix: don't import from tinygrad in sz.py 2023-12-18 20:49:46 -08:00
George Hotz
6617dcf095 move graph to runtime, check line count with sz.py (#2842) 
* move graph to runtime, check line count with sz.py

* oops, didn't save

* dtype aliases

* restore comment, REALCOUNT
 2023-12-18 20:30:06 -08:00
chenyu
15dc5bcfbd remove cstyle hip functions that deals with different types of input (#2840) 2023-12-18 22:43:22 -05:00
chenyu
dad9253d52 minor clean up in kernels (#2832) 
clean up some long lines and combined some short lines
 2023-12-18 19:35:59 -05:00
George Hotz
954a2fef75 hotfix: add JITGRAPH and invert sints 2023-12-18 16:33:22 -08:00
George Hotz
80f53245e8 shapetracker add and invert (#2828) 
* invert (broken)

* decent invert

* shapetracker invert works

* plus is meh, invert is good

* support invert mask

* a few more invert tests

* shapetracker math invert test
 2023-12-18 16:03:27 -08:00
chenyu
73cadfbb3c Remove pytest markers (#2831) 
* remove pytest marker

* fix some, skip some

* tweak

* fix

* skip slow

* skip more
 2023-12-18 18:53:28 -05:00
chenyu
264fe9c93f clean up test_dtype.py (#2827) 
make is_dtype_supported a pure function and clean up long lines
 2023-12-18 16:06:09 -05:00
chenyu
20ea43b6e7 dtypes.from_py to convert py types to dtypes (#2826) 
also updated some tests to test against default dtypes
 2023-12-18 14:23:31 -05:00
chenyu
0723f26c80 dtypes.default_float and dtypes.default_int (#2824) 2023-12-18 12:21:44 -05:00
chenyu
8aab19ce3d Tensor.full of bool has dtypes.bool (#2823) 2023-12-18 10:51:17 -05:00
chenyu
220abcd8ff fix squeeze of 0-dim Tensor with negative dim (#2821) 
if ndim=0, only accepted dim is 0, -1, None. other negative dim results in IndexError
 2023-12-17 22:02:07 -05:00
chenyu
21ec7e09f6 minor cleanup of image (#2820) 
use transpose for transpose instead of permute, and use pad for pad instead of slice
 2023-12-17 20:53:49 -05:00
chenyu
959d9cfed4 clean up ops_torch and ops_cpu (#2819) 2023-12-17 19:35:19 -05:00
Rory Clear
f409b57854 update metal matmul and matvec for new device style (#2732) 
* update for new device style

* create device before compile

---------

Co-authored-by: chenyu <chenyu@fastmail.com>
 2023-12-17 16:15:07 -05:00
chenyu
91adb119b8 remove match_type in ops_torch and ops_cpu (#2817) 
* remove match_type in ops_torch and ops_cpu

input dtypes are aligned and casted in mlops

* dict union only after python3.9

* fix that

* fix Sigmoid forward cast
 2023-12-17 15:32:30 -05:00
Maksym Sobolyev
887f3d9933 Make torch backend more usable, fix bfloat support in the llvm backend (#2765) 
* Uncripple dtype tests, TestBFloat16DType never actually runs.

* Fix conversion from/to bfloat16.

Call cast() recursively, so that it works for any type combo.

* Run this test on torch backend as well.

* Add torch.bfloat16.

* Add support for ushort and uint.

* Convert np.uint32 to np.int32 when loading.

* Fix warning.
 2023-12-17 14:04:26 -05:00
chenyu
9c32474a1f Revert "Revert "Tensor.randint is Tensor.uniform with dtypes.int32 (#2801)" (#2802)" (#2814) 
This reverts commit fa84998244.
 2023-12-17 12:14:17 -05:00
chenyu
b4fa189c8c Revert "Revert "Make Tensor creation allow multi-dim list of int and bool (#2793)" (#2810)" (#2813) 
This reverts commit 71a60762ed.
 2023-12-17 11:48:27 -05:00
Marcus Asteborg
1fa4f161fe Update CLProgram to use unsigned long long for event profiling (#2808) 
On Windows, the unsigned long type is 32-bit, which is not compatible
with the required data size for event profiling.
 2023-12-16 23:48:44 -08:00
chenyu
c333bfcf69 replace a defaultdict counting with Counter in cstyle (#2809) 
also removed a questionable Any annotation
 2023-12-17 02:44:16 -05:00
chenyu
4e2a92cee1 run HALF GPT2 in nvidia benchmark in addition to HALF/BEAM (#2811) 
easier to separate the issue between HALF and BEAM when it failed
 2023-12-17 02:24:55 -05:00
George Hotz
bad0ff60b7 start Qualcomm GPU driver (#2804) 
* hooking works

* working

* qcom work

* parsing command buffers

* proper parse
 2023-12-16 23:10:50 -08:00
chenyu
71a60762ed Revert "Make Tensor creation allow multi-dim list of int and bool (#2793)" (#2810) 
This reverts commit 798bf813b1.
 2023-12-17 02:03:52 -05:00
geohotstan
798bf813b1 Make Tensor creation allow multi-dim list of int and bool (#2793) 
* the universe is flat as a 2D tensor

* try this

* TESTS

* less lines in test

* don't change all_int since other places use it

* add tests and del noqa by making non-aesthetic spacing LOOOOOL

* some reordering

* fixed empty list and add tests

* more tests

* add list bool tensors

* clearer with least lines added

* added bool

* oops

* more tests

* improved tests

* oops
 2023-12-17 01:58:10 -05:00
chenyu
85c6250a3e support Tensor.einsum with no "->" in formula (#2807) 
output is the sorted alphabets if there's no "->"
 2023-12-17 00:46:24 -05:00
chenyu
157c0be509 cleanup onnx, pass one more reshape test and remove some casts (#2806) 2023-12-16 20:40:43 -05:00
chenyu
baa94d6142 Tensor(False) has dtypes.bool (#2805) 2023-12-16 19:04:08 -05:00
chenyu
fa84998244 Revert "Tensor.randint is Tensor.uniform with dtypes.int32 (#2801)" (#2802) 
This reverts commit 86c2f267d4.
 2023-12-16 15:53:28 -05:00
chenyu
86c2f267d4 Tensor.randint is Tensor.uniform with dtypes.int32 (#2801) 2023-12-16 15:14:50 -05:00
chenyu
0bb5d8f956 Revert "Green Uop unary check (#2792)" (#2799) 
This reverts commit d958777aed.
 2023-12-16 12:49:28 -05:00
qazal
d958777aed Green Uop unary check (#2792) 
* assert UnaryOps has same dtype as input in uop

* fallback to float on images

* just unary ops for now

* pass amt

* noqa on the temp line

---------

Co-authored-by: chenyu <chenyu@fastmail.com>
 2023-12-16 12:43:53 -05:00
George Hotz
051402625e remove pushing contig + fix linearizer bug (#2798) 
* remove that logic

* fix test, move LOADs

* fix repeat issue on LLVM

* with_phi
 2023-12-16 09:36:31 -08:00
Ahmed Harmouche
a7264dcb2b inf hack that works on chrome and wgpu (#2712) 
Co-authored-by: George Hotz <72895+geohot@users.noreply.github.com>
 2023-12-16 11:49:37 -05:00
George Hotz
877c78b4ce lazy tests (#2796) 
* tests

* mini sd is very mini
 2023-12-16 08:24:21 -08:00