github/tinygrad
1
1
Fork 0
mirror of https://github.com/tinygrad/tinygrad.git synced 2026-01-23 13:58:00 -05:00
Code Issues Packages Projects Releases Wiki Activity
1,989 Commits 204 Branches 14 Tags
dca084f227eb3266bb7ef36dde197cd6cd63e955
Commit Graph

1989 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
George Hotz
dca084f227 minor == to is touchups 2023-06-15 17:11:12 -07:00
blake
041d96083c clang rt for msvc (#986) 
* added platform config for clang runtime and tempfile dir for xplatform /tmp

* flake8 lint

* mypy lint

* pythonic?

* python?

* return darwin cflags

* <lines

* lint;
 2023-06-15 17:06:44 -07:00
George Hotz
039f0d372f delete ltypes (#984) 
* delete ltypes

* only upcast float types

* test dtype on mac passes

* ugh, these upcasts
 2023-06-15 16:24:45 -07:00
Yahya Lmallas
804c45b5fc FIX: Can't pickle local object (#979) 
_early_exec_process is a local function that is defined whiting the scope of another function, should be global
 2023-06-14 12:32:17 -07:00
Rayan Hatout
2d567ef688 Optimizations in tensor.py (#974) 
* optimizations in tensor.py

* make mypy happy

* revert split of Function class
 2023-06-14 08:44:35 -07:00
Diogo
0629791cbd F64 support (#976) 
* initial commit

* added osx check for opencl

* added llvm f64 conversions

* typo in llvmir

* more tests and modified unsupported error

* fixed linting error

* added pragma fp64

* simplified exclusion for OSX

* fixed device check and also added it to cast func

* added ifdef check for fp16 in ops_gpu

* Revert "added ifdef check for fp16 in ops_gpu"

This reverts commit 92de754d48.

* f64 prekernel signature match f16

* moved condition to buffer init
 2023-06-13 21:31:31 -07:00
John Moore
45bc040a63 Fix typo (#978) 2023-06-13 15:15:45 -07:00
George Hotz
80e665bddb a couple new tests 2023-06-13 12:36:05 -07:00
George Hotz
ba4eadb04c PTX assembly support (#977) 
* ptx assembly

* all ops tests pass

* fix tests
 2023-06-13 12:31:42 -07:00
Rayan Hatout
727416201f Shapetracker optimizations (#966) 
* optimizations in shapetracker.py

* revert micro-optimizations in assertions

* make mypy happy

* list comp instead of map in get_unsafe_resize_offset

* list comp instead of map in get_unsafe_resize_offset
 2023-06-12 18:13:21 -07:00
cloud11665
5f13e7c3cf cuda: fix fp16, uint8, int64, half4 codegen (#968) 
* cuda: add uchar, int64 typedefs

* cuda: fix float16 codegen

* fuck it, half4 stub. llama time!

* inline fp16 half4, revert changes to CStyleLanguage

* add inline just in case

* remove half4 operators

* use dict
 2023-06-12 11:15:44 -07:00
Steven Anderson
e54b6c5e7f One hot (#972) 
* passing with 1d indices

* passing all test

* cleanup

* using safe_numpy for scalar
 2023-06-12 10:13:29 -07:00
Diogo
613c74ca9f maintain input tensor dtype (#969) 2023-06-12 10:12:47 -07:00
Diogo
2d4370b487 Adds tril & triu support (#936) 
* triu & tril support

* lint and kernel count error

* switched shape indicies

* larger shape tests

* reverted numpy removal until #942 is resolved
 2023-06-09 22:13:20 -07:00
George Hotz
48e9461197 broken tests for #862 and #942 2023-06-09 22:02:59 -07:00
George Hotz
c62c64f0b7 remove GeNode (#965) 2023-06-09 21:48:56 -07:00
George Hotz
2c324d0685 fix metal uaf (#964) 2023-06-09 21:28:06 -07:00
Steven Anderson
c0e558b77c Test nllloss (#958) 
* works but slow

* work with NC and NCd1 it still slow

* refactor

* support for k dimensions

* without numpy
 2023-06-09 09:00:29 -07:00
Diogo
6b1280f01c fixes to Onnx ops LayerNormalization/Prelu and added OptionalHasElement/OptionalGetElement (#956) 
* prelu and where casting

* typing for safe_numpy

* optional

* get rid of tracing in ci

* cleanup and resolved layernorm issues

* removed debug print
 2023-06-08 16:09:19 -07:00
Nicklas Boman
5c7248c72d imagenet download and prepare (#928) 
Changing if not exist to the exist_ok=True parameter and adding a variable check if you want to download training data also
adding variable to env_vars.md
 2023-06-08 12:55:33 -07:00
George Hotz
df40a9c238 EXP+LOG -> EXP2+LOG2 (#954) 
* EXP+LOG -> EXP2+LOG2

* update docs
 2023-06-08 10:57:31 -07:00
Diogo
666d151f8a Onnx slice fixups (#952) 
* resolved some slice test errors and added some more debugging logs

* use same device in cumsum

* increased float priority

* onnx debug ouput match input
 2023-06-07 19:44:30 -07:00
cloud11665
e8a23d4331 there is a better way to do that! (#950) 2023-06-06 15:23:30 -07:00
SnakeOnex
990fc40219 made seed None by default -> numpy picks a random seed (#946) 
* made seed None by default -> numpy picks a random seed

* fixed _seed type

* set the seed to unix timestamp

* make filetype int only
 2023-06-06 13:06:23 -07:00
Timothy Lindblom
a149f12a5b Replaced broken link to /tests with /test (#939) 2023-06-06 10:29:09 -07:00
M4tthewDE
664d6cc7e5 Implement onnx MeanVarianceNormalization (#943) 2023-06-06 10:28:19 -07:00
Diogo
3bb38c3518 limit split to 1 due to windows path containing : (#944) 2023-06-06 10:27:54 -07:00
Steven Anderson
079ea217a3 fix test_pow_type - autocasting for Pow with inputs of diff type (#937) 2023-06-05 15:22:35 -07:00
George Hotz
76ab379f9b readme updates 2023-06-05 12:20:14 -07:00
cloud11665
43ea1614b0 fix inf/nan codegen (#935) 
* fix inf/nan codegen

* remove nasty oneliner, fix -inf

* inf/nan const mul/div tests
 2023-06-05 11:24:09 -07:00
Filip Dimitrovski
78460034ff Initial ellipsis support when slicing Tensors (#843) 
* Initial ellipsis support when slicing Tensors

* Better comments in ellipsis slicing

* Formatting
 2023-06-05 07:52:49 -07:00
M4tthewDE
70f12fdb57 Fix wrong op version being used if versions equal (#934) 2023-06-05 07:45:10 -07:00
Steven Anderson
79613eb83e Test min (#932) 
* fix __neg__ defaulting to float32 due to 0.0

* fixed __neg__ always defaulting to float32

* fixed openpilot (OpenCL) Test
 2023-06-05 00:03:30 -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
Tom Edwards
5bbcbd145c Add cumsum with n-dim inputs (#922) 
* add cumsum with n-dim inputs, over arbitrary axis + relevant tests

* increased rtol for cumsum test

* move test_cumsum into test_ops

* skip arange test for images as relies on cumsum

* Fix typo

* rewrite cumsum to work with images
 2023-06-04 16:55:23 -07:00
wozeparrot
091bd65a68 feat: quick doc fixups (#923) 2023-06-04 11:03:57 -07:00
George Hotz
fbf17f0031 intel benchmark matmul gets 60 TFLOPS? 2023-06-04 17:01:50 +00:00
Steven Anderson
657e642e3a Fixed test suite for Clip (#912) 
* Fixed test suite for Clip

* fixed issue with clip when taking large negative numbers as min

* Remove typings
 2023-06-04 09:01:01 -07:00
kposborne2
0b88c5f923 Eliminate LoadOps.FROMCPU (#920) 
* Add fromCPU method to init LazyBuffer to eliminate LoadOps.FROMCPU

* squish

* remove failing test

* seems logical

* Revert "seems logical"

This reverts commit bbdcdc8713.

* inline and remove assertion

* fromCPU staticmethod, defer non-cpu device to loadop

* restore test
 2023-06-04 08:55:50 -07:00
George Hotz
3e0b37f050 randn slow 2023-06-04 08:52:13 -07:00
wozeparrot
e9c1ae3825 Add a quick start guide (#900) 
* feat: initial quick start guide

* fix: fix link

* feat: add note about jit

* feat: add note about load/store ops

* feat: add link to discord

* feat: add note about saving and loading models

* fix: correct code for saving and loading

* feat: overhaul docs

* fix: fix link

* feat: wording

* feat: add link to discord

* feat: contributing guidelines

* feat: make contributing section more doc focused

* feat: add link to env_vars from readme

* fix: wording

* feat: move community to bottom

* feat: showcase

* feat: linebreak

* feat: redesigned header

* feat: tweaks

* feat: tweaks

* feat: badge for lines of code

* feat: move installation instructions to repo readme

* feat: readme overhaul number 2

* feat: move visualization to quick start guide

* feat: readme 2 electric boogaloo

* fix: grammar

* fix: formatting

* feat: no ugly line

* feat: add line back

* feat: new load method

* feat: split adding accelerator docs out

* feat: showcase whisper

* feat: smaller tweaks

* feat: bring back oneliner
 2023-06-04 08:51:20 -07:00
Alexey Zaytsev
d429553730 Allow Tensor(tuple) (#911) 2023-06-03 23:48:19 -07:00
George Hotz
afd0be8a9c intel example 2023-06-04 06:43:09 +00:00
MohammedAlkhrashi
2b4baa97e9 exclude string type from external_test_onnx_backend.py (#918) 2023-06-03 19:10:52 -07:00
George Hotz
b78addf2f8 Whisper (#919) 
* no whispering yet

* whispering

* live whisper

* small support
 2023-06-03 18:55:14 -07:00
George Hotz
ed1963b899 Fast DiskTensor to other Tensor (#916) 
* make disktensors fast

* loading

* loader for sd and llama
 2023-06-03 12:25:41 -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
d58586bb17 safetensors! (#903) 
* safetensors test

* safe_save

* load back with real safetensors

* bugfix in device name. add simple torch_load

* it works for llama, but it's slower...

* mmap

* no intermediate

* load mmaped

* readinto speed

* not ready yet

* revert that
 2023-06-02 13:41:09 -07:00
Steven Anderson
513aeb2f66 Fixed all ConstantOfShape test suite (#907) 2023-06-02 11:26:40 -07:00
Steven Anderson
301f7b54c6 ConstantOfShape ONNX test fixed. (#890) 
* ConstantOfShape ONNX test fixed.

* removed redundant if statement

* value is optional and should default to a float32 tensor with value of 0

* fixed: default parameters are created at function definition, bad for mutable objects.
 2023-06-02 07:34:25 -07:00