24 Commits

Author SHA1 Message Date
George Hotz
a6d842af7a move device to ops (#1646)
* move device to ops

* mlops types

* 2 lines
2023-08-23 08:30:17 -07:00
chenyu
ae39cf84ab Symbolic Shape JIT main PR (#1353)
* Symbolic Shape JIT

update tests

2 variables symbolic ops, adding more tests

test passing

cleanup

* more test cases

* single flag

* review update

* jit attention one piece

* realize

* symbolic_jit test for cuda

* old artifact

* works with cuda gpu but failed ci

* CUDACPU
2023-08-18 14:39:55 -07:00
George Hotz
d24f936501 just cmplt (#1493)
* just cmplt

* fix maximum

* don't save, there's no backward

* ugh, no slot either

* eq is a scam
2023-08-08 13:58:10 -07:00
George Hotz
7b8d06c9f1 test uops (#1444)
* test uops

* tests should pass

* improve uops

* precision
2023-08-05 12:35:56 -07:00
George Hotz
84c430355e fix backends for new style (#1443)
* fix backends for new style

* fix method cache

* fix fakeless

* llvm blacklist

* fix kernel optimizer
2023-08-05 11:07:04 -07:00
chenyu
940b6fd21a Revert "Fix constant folding for Tensor([3]) (#1227)" (#1274)
This reverts commit ab645317c9.
2023-07-19 10:51:06 -07:00
David Hou
56ee97b37f dedup kernel args v2 (#1272)
* new version

* fix abstractions

* try remove test

* Revert "try remove test"

This reverts commit 2fc18a9f8e.

* assert_allclose

* minimize the test

* minimize the test

* minimize the test

* minimize the test

* Revert "minimize the test"

This reverts commit e0c0929596.

* Revert "minimize the test"

This reverts commit 88240551b1.

* Revert "minimize the test"

This reverts commit 78328a7ce2.

* Revert "minimize the test"

This reverts commit 989523fded.

* skip test inside body

* oops

* oops
2023-07-18 20:03:42 -07:00
Adrian Kretz
5a8ad57163 Add WHERE ternary (or trinary?) op (#1196)
* Rename FusedOps to TernaryOps

* Support ternary broadcast

* Add where llop and mlop

* Make where op work in cstyle codegen

* Don't skip test_inf_where

* Add backward path to where op

* Use bool in cstyle codegen

* Add LLVM where op

* Add numpy where op

* Add torch where op

* Simplify where mlop

* Update documentation

* Forgot a rename

* Merged relevant changes from PR #1195 onto PR #1196

* Add test to cover changes to linearizer.ast_parse for WHERE op

Without this METAL will try to use ternary op on float4 and fail

* Make where op work in wgsl backend

* Allow ternary ops to be merged

* Make mypy happy

---------

Co-authored-by: Francis Lam <flam@alum.mit.edu>
2023-07-16 00:31:55 -07:00
chenyu
ab645317c9 Fix constant folding for Tensor([3]) (#1227)
* Fix constant folding for Tensor([3])

* Remove duplicated prod import

* load in the same device

* better numpy

* add constant fold shape test cases

* improve tests
2023-07-11 14:01:32 -07:00
George Hotz
2952b8e7a8 Fix up abstractions.py to include the Linearizer (#1177)
* fix up docs

* remove pow, add sqrt
2023-07-07 18:33:51 -07:00
tricky-labyrinth
fd98f6cffa Small fix to abstractions.py so it runs on Windows without throwing an AttributeError (#1109)
Co-authored-by: Tricky Labyrinth <trickylabyrinth@gmail.com>
2023-07-03 13:44:49 -07:00
ernie
4d703be6d7 fix typo (#1065) 2023-06-27 10:56:54 -07:00
George Hotz
df40a9c238 EXP+LOG -> EXP2+LOG2 (#954)
* EXP+LOG -> EXP2+LOG2

* update docs
2023-06-08 10:57:31 -07:00
kposborne2
00360da05b Update broken docs/abstractions.py for changed ops, and add to CI (#930)
* fix and add to ci

* still have those

* ocd

* update other doc
2023-06-04 19:21:20 -07:00
George Hotz
791530045d Refactor LoadOps (#910)
* test

* work

* upd test

* loadops

* cleanups

* real ones

* remove LazyNumpyArray

* fix assign test

* remove range

* np.require

* llama uses arange kernels

* no caching consts

* fix enet

* torch load support

* tests cleanup

* fix shufflenet

* fix image

* fix torch_load test
2023-06-03 09:40:43 -07:00
George Hotz
f5467cfedc Devicebufferless (#708)
* runs one metal kernel

* conv2d works

* ops tests are passing

* const folding

* all ops work

* pre commit always passes

* torch works

* working still

* fix graph test

* tests passing

* image almost works

* image conv works

* most images

* fix custom

* fix assignment

* fix compile enet

* clean up comments

* fix realize return value

* include shapetracker in LB repr

* copy should make a copy

* reenable method cache

* fix lna

* dtypes in graph

* forward only for IMAGE=2

* simple realize

* getting close

* fixup new api, it's good except the kernel count

* back to 197 kernels

* tests should pass

* go to a real float

* no type_on_cpu

* fix the docs

* put shapetracker back in it's proper place
2023-03-18 14:40:23 -07:00
George Hotz
3a8af99adb i understand ClassVar now 2023-03-15 09:00:25 -07:00
Pasan Perera
df48753692 fixed the import error for latest changes in master (#705) 2023-03-15 08:59:42 -07:00
George Hotz
54f499b623 Move rawbuffer (#697)
* move GlobalCounters to helpers

* that's not part of the public api

* move InterpretedBuffer

* remove fromCPU from devicebuffer
2023-03-13 22:30:36 -07:00
George Hotz
cbc5a7222a symbolic is now a 6/10 due to the infinite loop. do better. 2023-03-13 00:07:59 -07:00
George Hotz
c594a0a835 fix flip bug, add new unit tests 2023-03-12 23:55:31 -07:00
George Hotz
ce1564b05e fix shapetracker test 2023-03-12 22:33:25 -07:00
George Hotz
153cce0f7e tutorial 2023-03-12 22:31:46 -07:00
George Hotz
8d16ebaea7 we have docs: 2023-03-12 19:05:44 -07:00