github/tinygrad
1
1
Fork 0
mirror of https://github.com/tinygrad/tinygrad.git synced 2026-04-07 03:00:26 -04:00
Code Issues Packages Projects Releases Wiki Activity
8,475 Commits 241 Branches 14 Tags
5265f25088872c68c220b362dcc840c48db2402e
Commit Graph

334 Commits

Author SHA1 Message Date
chenyu
8c6299bced move hand_coded_optimizations to heuristic.py [pr] (#9844) 
* move hand_coded_optimizations to heuristic.py [pr]

also folded all long lines

* make a copy and rename self -> k

* fix test
 2025-04-10 23:40:16 -04:00
George Hotz
78caf55154 Revert "FP8 support on NVIDIA (#8631)" 
This reverts commit 2c8e4ea865.
 2025-04-09 12:27:41 +08:00
pkotzbach
2c8e4ea865 FP8 support on NVIDIA (#8631) 
* squashed fp8 commits

* tensorcore start

* minor changes

* pre-commit

* pylint

* Delete fp8mul.cu

* clean

* small bugfix

* fix test_dtype

* fix test_dtype_alu

* add EMULATE_CUDA_SM89

* fix ci

* fix test_linearizer

* fix test_linearizer

* fix swizzle

* add debug to simple_matmul

* fixed swizzle

* python emulator

* refactor python emulator

* setup fix

* numpy setup

* ml_dtypes only in emulate_cuda_sm89

* fix pylint

* fix tests

* fix mypy

* fix mypy

* fix ruff

* done python emulator

* add acc type

* tests

* mypy

* clean code

* add cuda tensor core tests to CI

* minor fix

* clean test_dtype.py

* clean cstyle.py

* clean test_ops.py

* fix test

* fix test

* whitespaces

* pylint

* pylint

* amd?

* amd?

* amd

* reduce lines

* mockgpu remove

* fix

* ruff

* ruff

* fix mypy

* ruff

* test only for cuda

* fixed formatting

* small fixes

* small fix

* least_upper_dtype if fp8s not supported

* log and reciprocal are supported for fp8s

* ops python fixes

* dtypes.fp8s use

* e4m3 + e5m2 result dtype test

* truncate linter fix

---------

Co-authored-by: pkotzbach <pawkotz@gmail.com>
Co-authored-by: George Hotz <72895+geohot@users.noreply.github.com>
Co-authored-by: chenyu <chenyu@fastmail.com>
 2025-04-08 21:54:04 -04:00
Ignacio Sica
58785181a8 AMD bf16xf32 TC (#9717) 
* dont test bf16 for emulated amd tc

* skip bf16 tc test in ci

* skip bf16 for AMD in test_tensor_cores_codegen

* add simple bf16 gemm test to benchmark
 2025-04-07 11:41:04 +08:00
George Hotz
cac8bcf8b5 use Ops.REDUCE (#9721) 
* decrease bert python time [pr]

* order copies

* Revert "order copies"

This reverts commit 3f62c8693b.

* rewrite count

* Ops.REDUCE

* acc first in the add chain

* Fix tensor core acc

* arange patterns look good

* fix multireduce gate

* reduce rewrite rule

* bump that to 15 minutes

* multiwmma isn't fusing

* gep through wmma is gep pushing

* bump that timeout too, it's all env setup

* add failing test
 2025-04-04 10:14:34 +08:00
Ignacio Sica
2d6d8b7355 add bf16 mfma support (#9695) 
* add bf16 mfma support

* skip tc if emulated_amd and dtypes is bf16

* hotfix
 2025-04-02 21:44:49 +08:00
George Hotz
e78e8722dc Revert "LDS noop and spec (#9669)" (#9691) 
This reverts commit 870b545ace.

Co-authored-by: Ignacio Sica <mignacio.sica@gmail.com>
 2025-04-02 15:31:32 +08:00
Ignacio Sica
870b545ace LDS noop and spec (#9669) 
* init lds noop and lds_0 spec

* refactor lds helper test

* fix typo

* test all lds at the same time

* change comment

* comment

* start test_lds_full

* test_lds_tc

* add tc spec
 2025-04-01 18:44:55 +08:00
b1tg
d9af4cfc1b AMD_LLVM: tensor cores support (#9613) 
* tensor cores support

* test tesor cores codegen

* use rewrite rules

---------

Co-authored-by: b1tg <b1tg@users.noreply.github.com>
 2025-04-01 09:56:27 +08:00
Ignacio Sica
1444069c09 Uppercase K for dimension and lowercase k for kernel in linearizer tc helper test (#9649) 2025-03-31 19:05:36 +08:00
Ignacio Sica
baa67fd124 Uppercase N and M (standalone syntax change) (#9647) 2025-03-31 18:45:30 +08:00
chenyu
f8976dd2eb enable more webgpu tests (#9502) 
OSX has larger buffer number limit, and it supports fp16 now
 2025-03-18 23:03:54 -04:00
George Hotz
117b7a16ef VALIDATE_WITH_CPU [pr] (#9488) 
* VALIDATE_WITH_CPU [pr]

* fix test
 2025-03-18 15:15:04 +08:00
chenyu
01e8b60911 acc_dtype -> dtype (#9402) 
matched numpy and torch
 2025-03-10 16:05:30 -04:00
George Hotz
ece0a0f305 use empty for test instead of rand (#9332) 2025-03-03 16:19:06 +08:00
George Hotz
2cc4cb74f0 reorder binops (#9328) 
* reorder binops

* test improvements + fix string tests

* ugh, okay this
 2025-03-03 14:58:18 +08:00
qazal
2eab8021fb remove inputs+outputs attributes from ScheduleItem [pr] (#9192) 
* remove inputs/outputs from ScheduleItem

* fix test_linearizer

* fix test_conv_shapetracker

* fix test_schedule + lint

* test_image_dtype + multitensor + search
 2025-02-21 13:48:11 +01:00
chenyu
2e7c2780a9 CLANG -> CPU (#9189) 2025-02-20 18:03:09 -05:00
George Hotz
a4dab3ec3f add name uop (#9149) 
* add name uop, TODO: refactor renderer to use

* renderer uses name uop

* fix tests

* render

* ptx
 2025-02-18 15:26:58 +08:00
Ahmed Harmouche
59fe45f947 Solve get_grouped_dims does not split issue (#9085) 
* Solve dims too large errors on webgpu

* Simplify divisor find

* Test square root divisor

* Fix lint

* Refactor into group_dims and split_dims

* Refactor

* Fix lint

* Add back max check in _group_dims

* Prefer grouping over split

---------

Co-authored-by: chenyu <chenyu@fastmail.com>
 2025-02-16 19:57:29 -05:00
chenyu
f53b819648 UOps. -> Ops. [pr] (#9044) 
updated the comments and doc except extra
 2025-02-12 12:53:23 -05:00
Ignacio Sica
aaed315fee add AMX support to LLVM (#8957) 
* init amx support for llvm

* revert elf changes

* fix attributes for AMX asm calls

* add comments

* add llvm amx job to benchmarks

* cleanup

* cleanup

* hotfix: improve comments

* comment for aux buffers

* hotfix:

* move amx_tc to ClangRenderer

* merge master

* refactor

* add docs

* add corsix docs reference

---------

Co-authored-by: George Hotz <72895+geohot@users.noreply.github.com>
 2025-02-12 16:01:18 +08:00
George Hotz
a3c78d47b3 speed docs + upgrades [pr] (#8964) 
* add some docs about speed [pr]

* better torch gemm

* enable locals on llvm/clang

* disable locals for beam speed on LLVM/CLANG

* 0x20 alignment in llvm allows ymm use
 2025-02-08 17:28:52 +08:00
George Hotz
c2b4c43edb handle stride 0 reduce (#8068) 
* handle stride 0 reduce [pr]

* more test fixups

* a few more

---------

Co-authored-by: qazal <qazal.software@gmail.com>
 2025-02-07 15:40:58 +01:00
Ahmed Harmouche
133cacadde Autogen webgpu dawn, removing wgpu-py dependency (f16 support part 1) (#8646) 
* Switch to dawn, all tests passing locally

* Use dawn-python

* Skip failing test

* Skip midcast and fix timestamp on metal ci

* Autogen webgpu

* Try fetch dawn lib again

* /usr/lib

* Without lib prefix

* Test autogen diff

* Delete webgpu support, move everything to ops_webgpu

* mypy fix

* Simplify, refactor

* Line savings

* No ResultContainer

* Type annotation for result

* Some more simplifications

* Why was this explicit sync used at all?

* Refactor: delete functions that are only used once

* Create shader module inline

* Clear unit tests cache, maybe that solves it

* That wasn't it

* Try deleting cache to pass failing weight compare

* weights_only=False for pytorch 2.6

* Simplify ctype array creation

* Remove nanosecond precision timestamps

* Simplify error handling

* Refactor, add back type annotations

* Deleted custom submit function, refactor

* read_buffer simplify

* Fix use after free, refactor

* Simplify supported_features

* Runtime docs

---------

Co-authored-by: George Hotz <72895+geohot@users.noreply.github.com>
 2025-02-07 15:16:59 +08:00
chenyu
a092b6395d Tuple -> tuple, List -> list [pr] (#8936) 2025-02-06 14:21:19 -05:00
Ignacio Sica
15f94ac964 TC_SEARCH_OVER_SHAPE to search multiple TC shapes (#8793) 
* squash search over search

* refactor assert

* init benchmark

* cleaner get_kernel_actions

* cleaner get_kernel_actions

* add comment
 2025-02-05 11:03:46 -05:00
Ignacio Sica
260df1a17f tc_select noop (#8801) 
* tc_select noop

* revert changes in test
 2025-01-29 13:53:23 -05:00
qazal
ba17786068 do not construct unmasked VALID (#8759) 
* new lines that exist in codegen/ops

* update tests

* update sops.gz (13071 -> 13070 asts)

* fix viz too

* remove that TODO

* diff pruning

* mask assert + device

* work

* diff pruning

* re: fix viz too

---------

Co-authored-by: George Hotz <72895+geohot@users.noreply.github.com>
 2025-01-28 20:51:21 +02:00
Ignacio Sica
b240f12593 [TIP-9] rename Opt's amt to arg 2 (#8770) 
* rename Opt amt to arg

* ignore_beam_cache for test_tiny

* move ignore_beam_cache to test_tiny

* move to separate pr

* revert space change

---------

Co-authored-by: chenyu <chenyu@fastmail.com>
 2025-01-27 14:19:04 -05:00
George Hotz
3ed146a5ff Revert "rename Opt amt to arg (#8767)" (#8769) 
This reverts commit bf041659a5.
 2025-01-27 23:46:37 +09:00
Ignacio Sica
bf041659a5 rename Opt amt to arg (#8767) 2025-01-27 23:36:47 +09:00
George Hotz
b4bf6a7dea switch backward to use gradient [pr] (#8235) 
* switch backward to use gradient [pr]

* set device correctly, dedup

* why does that fail?

* add noop cast

* simple backward

* fix beautiful_mnist

* touchups

* set in compute_gradient

* uop_count

* uop_count was wrong

* collections

* no note

* skip that test

* update sched kernel counts

* train mnist is 65

* fix metadata and gc

* fixes

* materialize_grads

* no pathlib stuff

* add contiguous_backward, fix bugs

* add some realize

* fix multi
 2025-01-26 09:12:16 +09:00
George Hotz
46a8c5e1e5 delete forced_realize (#8615) 
* delete forced_realize

* put that back

* expectedFailures

* cleaner create_subbuffer

* more comments

---------

Co-authored-by: qazal <qazal.software@gmail.com>
Co-authored-by: qazal <77887910+Qazalin@users.noreply.github.com>
 2025-01-20 09:40:36 -08:00
qazal
d957a4f108 add tests for div buffer collapsing in the scheduler [pr] (#8671) 
* add tests for mul/div buffer collapsing in the scheduler [pr]

* lint

* merge with test_linearizer's version of this

* 4*3
 2025-01-18 14:15:29 -05:00
ignaciosica
d2234e308a tf32 tc for nv and ptx (#8635) 
Co-authored-by: George Hotz <72895+geohot@users.noreply.github.com>
 2025-01-17 17:43:57 -08:00
qazal
ae2229d727 assert kernel buffer limit at compile time [pr] (#8595) 
* remove the BUF_LIMIT assert

* skip the base one
 2025-01-13 16:32:07 -05:00
qazal
586e730d32 use UOp.st for kernel reduce axes (#8499) 
* use UOp.st for kernel reduce axes [pr]

* do not return dict
 2025-01-13 06:24:11 -05:00
qazal
866dfa1f23 create_schedule([x.lazydata]) -> x.schedule() in tests (#8449) 2024-12-31 03:15:52 +08:00
George Hotz
29c14f1cbf hotfix: update tests for no uop mut 2024-12-30 10:05:37 -05:00
ignaciosica
ba0c844a83 special tol when f16 and bf16 are tc input dtypes (#8183) 2024-12-21 11:32:26 -05:00
George Hotz
bd9c015b09 tests from grad uop path [pr] (#8313) 2024-12-18 09:25:05 -08:00
Ahmed Harmouche
a73e3677d0 Test linearizer on webgpu (#8159) 
* Test linearizer on wgpu

* Skip tests due to exceeded dims
 2024-12-11 17:03:26 +01:00
qazal
6be388be86 failing test for const folding breaking indexing [pr] (#8103) 2024-12-07 19:55:02 +08:00
George Hotz
0c7477b108 no bool in range [pr] (#7988) 
* no bool in range [pr]

* fix llvm

* add arg to range spec

* fix broken test

* forgot this one

* hotfix: test_tiny jit is a real test
 2024-12-02 19:05:16 +08:00
George Hotz
f17af70d17 replace all sparents with toposort (#7983) 2024-12-02 15:00:30 +08:00
George Hotz
c5c3b05b5a block lin: only the test changes (#7933) 2024-11-28 13:19:00 +08:00
George Hotz
32dbab945c Revert "add block uops and modify tests (#7931)" (#7932) 
This reverts commit 6f4519ff45.
 2024-11-28 13:15:41 +08:00
George Hotz
6f4519ff45 add block uops and modify tests (#7931) 2024-11-28 13:11:18 +08:00
chenyu
a58e289d77 Revert "prereqs for new block lin so PR works (#7919)" (#7921) 
This reverts commit c53261b541.
 2024-11-27 08:41:09 -05:00