geohot/tinygrad
1
0
Fork 0
forked from tinygrad/tinygrad
Code Pull Requests Actions Activity
7,960 Commits 4 Branches 15 Tags
1db4341e9fb3a6b4e0307597ea70ec44b321e461
Commit Graph
7960 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
qazalandGitHub 1db4341e9f move viz graph to lib/graph [pr] (#9196) 
* move viz graph to lib/graph [pr]

* add package

* share with program
 2025-02-21 21:04:07 +01:00
geohotstanandGitHub 6587c7879b simple fixes to onnx (#9195) 
* uncontroversial changes

* cleaner _prepare_quantize
 2025-02-21 13:10:06 -05:00
Simon RandGitHub 2318d7ac51 Add missing tinygrad.runtime.autogen.am to packages (#9194) 2025-02-21 15:38:24 +02:00
qazalandGitHub 8bb80b6e5e reorder AST matchers + comments [pr] (#9193) 2025-02-21 14:31:15 +01:00
qazalandGitHub 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
George HotzandGitHub e87be0131e torch backend start (#9191) 
* start torch backend

* progress

* ugh, you need cpp crap

* 1+1 works

* 1+1 works

* becoming a real backend

* ready to merge?
 2025-02-21 16:57:28 +08:00
geohot d3a21cced2 hotfix: bump version to 0.10.2 v0.10.2 2025-02-21 10:43:49 +08:00
chenyuandGitHub 2e7c2780a9 CLANG -> CPU (#9189) 2025-02-20 18:03:09 -05:00
nimlgenandGitHub f986e12f91 metal: choose compile spec based on macos (#9188) 
* metal: choose compile spec based on macos

* correction
 2025-02-21 00:43:39 +03:00
chenyuandGitHub 3e22747799 run unit test on windows ci (#9187) 
* factor out testing_minimal in setup.py [pr]

* testing_unit + windows
 2025-02-20 14:40:41 -05:00
chenyuandGitHub 287de4ecc6 use torch in test_gradient (#9186) 
used torch.autograd.grad, but not sure if it can be a template like jax
 2025-02-20 12:26:11 -05:00
qazalandGitHub 574a905291 Fix running VIZ=1 after package installation + test (#9183) 
* test running viz from pip install

* add pkg

* do 10 connection attempts

* include assets in package_data

* quiet curl

* better print
 2025-02-20 15:02:00 +01:00
chenyuandGitHub 1692087db5 _one_hot_along_dim input needs to be int (#9179) 
* _one_hot_along_dim input needs to be int

indexing and onehot compare with arange, and non-int dtype is likely a bug
 2025-02-20 09:00:43 -05:00
George HotzandGitHub bf36967883 cuda hooking (#9180) 
* cuda hooking

* progress

* more hook cuda

* fix params

* compile + cuMemHostAlloc hook

* work

* revert that
 2025-02-20 19:20:01 +08:00
chenyuandGitHub 3b37cc898b add bert tiny config (#9177) 
set with BERT_SIZE=tiny. easier to study embedding and fusion
 2025-02-19 14:57:03 -05:00
qazalandGitHub 5662c898f1 correctly step through bottom_up_rewrites in viz [pr] (#9176) 2025-02-19 19:20:57 +01:00
peppingdoreandGitHub b1ddb2a1a6 fix win32 CPUProgram missing cache flush (#9171) 
* win32: fix missing inst cache flush, rename ptr->self.mem for consistency with posix code

* fix types, remove assert

* fix memory leak

* rm whitespace
 2025-02-19 21:38:51 +08:00
qazalandGitHub 1bb9d78c7a hotfix: add output buffer back to kernel parents + comment [pr] (#9174) 2025-02-19 14:22:01 +01:00
chenyuandGitHub 975c318dbc bert use int32 for input ids (#9173) 
original data was int32 for these. float might have caused precision issues
 2025-02-19 08:17:27 -05:00
qazalandGitHub e4a8bf28ea scheduler cleanups + better cycle assert [pr] (#9172) 
* scheduler cleanups + better cycle assert [pr]

* type_verify after assign fixup

* don't need base

* always realize sink parents
 2025-02-19 13:30:58 +01:00
qazalandGitHub cf315d544b rename can_pad arg to cache [pr] (#9170) 2025-02-19 12:24:59 +01:00
qazalandGitHub 2fc8bf115d remove support for VIEW with two sources in ops [pr] (#9168) 
* only 1 src views can exist [pr]

* views can still exist without a base, this is a separate project
 2025-02-19 11:10:18 +01:00
Ahmed HarmoucheandGitHub a2afa523a0 Only add enable f16 directive if ShaderF16 is supported (#9163) 
* F16 in check in wgsl renderer

* Default in renderer to fix pickle

* Refactor f16 check
 2025-02-19 17:20:03 +08:00
Ahmed HarmoucheandGitHub 0f94b98646 Force WebGPU backend type [pr] (#9164) 
* Force webgpu backend type

* Mypy fix

* Rename to WEBGPU_BACKEND

* Add it to env_vars docs

* Remove link
 2025-02-19 17:19:39 +08:00
qazalandGitHub 4bc708a9b0 do not create buffers we never realize in scheduler (#9165) 
* work

* delete

* fix

* works

* FUSE_CONV_BW

* FUSE_ARANGE

* becomes_map

* fix assign p1

* fix assign (diamond) - 2

* fix test_assign_double_diamond_reduce

* fix subbuffer

* faster rewrite

* fix simple_pads

* start metadata work

* do some diff cleanups

* make things that can't be images not images

* openpilot fix

* fix linter

* diff

* minimal diff

* more work on the diff

* metadata
 2025-02-19 10:11:47 +01:00
George HotzGitHubqazal
 		1c4e9bc363 image fixup tensor map [pr] (#8611) 
Co-authored-by: qazal <[email protected]>
 2025-02-19 10:11:06 +02:00
qazalandGitHub 2a5fe3e700 whitespace changes from the map_tensors branch [pr] (#9167) 2025-02-19 09:52:59 +02:00
qazalandGitHub a773ff73e3 match image cast folding on the cast itself [pr] (#9166) 2025-02-19 09:31:34 +02:00
qazalandGitHub 9a20063837 create subbuffer immediately before constructing ScheduleItem [pr] (#9162) 2025-02-18 21:07:52 +01:00
qazalandGitHub 1c92534bff hotfix: viz should show if there's a rewrite [pr] (#9161) 2025-02-18 19:11:03 +01:00
George HotzandGitHub a330f3338c save applied opts in ProgramSpec [pr] (#9150) 2025-02-19 00:40:03 +08:00
chenyuandGitHub ff05bff221 put bert data shard inside jit (#9160) 
python time 45ms -> 9ms, it was spending time to schedule the shard

also init bert data on CLANG since it's from numpy, so we don't create the tensor on default device then shard into GPUS
 2025-02-18 10:36:54 -05:00
qazalandGitHub 679291e26a assert only base maps to buffer [pr] (#9159) 2025-02-18 15:46:47 +01:00
qazalandGitHub 4f592eeea6 hotfix: remove extra matcher for copy/buffer_view [pr] (#9157) 2025-02-18 13:21:24 +01:00
geohot ff9b985d9f hotfix: View Base AST 2025-02-18 18:48:34 +08:00
George HotzandGitHub 30f470eaa3 UNIQUE UOp for buffer instead of arg (#9156) 
* UNIQUE UOp for buffer instead of arg

* factor out buffer spec
 2025-02-18 16:59:59 +08:00
qazalandGitHub 38f5ea2132 increment writable buffers refcount from the kernel graph [pr] (#9153) 2025-02-18 10:20:02 +02:00
George HotzandGitHub ddddcc165b colors back in DEBUG=2 [pr] (#9155) 2025-02-18 16:17:57 +08:00
George HotzandGitHub 6d62966bf7 add support for named rewrites [pr] (#9152) 2025-02-18 16:07:04 +08:00
George HotzandGitHub caee42e8a6 Revert "name from uops [pr] (#9151)" (#9154) 
This reverts commit 28897be9a2.
 2025-02-18 16:06:44 +08:00
George HotzandGitHub 28897be9a2 name from uops [pr] (#9151) 2025-02-18 15:52:03 +08:00
George HotzandGitHub 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
George HotzandGitHub 2db8b4046a minor linearizer refactor to finalize in rewrite [pr] (#9148) 2025-02-18 12:42:22 +08:00
George HotzandGitHub df3b320f46 rewriter -> devectorizer [pr] (#9147) 2025-02-18 12:42:08 +08:00
chenyuandGitHub 5dc1257ce0 clean up bert fake data iterator [pr] (#9145) 
reuse the same get_data_bert path in setup and real run
 2025-02-17 20:03:38 -05:00
qazalandGitHub 751c517b6c cancel viz request after the kernel clicked away [pr] (#9144) 2025-02-17 20:19:09 +01:00
chenyuandGitHub 465421b525 fix Tensor.isclose (#9143) 
many corner cases around inf and nan
 2025-02-17 12:03:12 -05:00
qazalandGitHub 36741cbbc1 enable real_size assert for test_conv_2x2_backward_one_view [pr] (#9142) 2025-02-17 17:53:44 +01:00
qazalandGitHub e9ff4ef4f7 s/ScheduleContext/GrouperContext [pr] (#9141) 
* refactor to kernel context [pr]

* s/ScheduleContext/GrouperContext [pr]
 2025-02-17 17:14:17 +01:00
qazalandGitHub 96cc9f59e0 refactor to kernel context [pr] (#9140) 2025-02-17 16:57:14 +01:00