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
8,403 Commits 241 Branches 14 Tags
bf769fa5c585a114c97f799e1a68e857965fb2b2
Commit Graph

8403 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
George Hotz
bf769fa5c5 label ranges with their number (#9805) 2025-04-09 14:31:18 +08:00
chenyu
c5db5b83b9 add SHOULD_USE_TC=1 check to simple_matmul (#9802) 
* add SHOULD_USE_TC=1 check to simple_matmul

also zero centered the random input and update atol for tf32

* ATOL=2e-2 for HALF
 2025-04-09 02:24:42 -04:00
qazal
f27dbc8c35 becomes_map cleanups [pr] (#9790) 
* cleanup becomes_map [pr]

* source
 2025-04-09 14:11:53 +08:00
qazal
7d2349c827 track_rewrites in scheduler [pr] (#9801) 2025-04-09 12:48:14 +08:00
George Hotz
bb18adb0d5 reduce with a mul chain (#9799) 
* reduce with a mul chain

* inside is just 1
 2025-04-09 12:42:32 +08:00
George Hotz
78caf55154 Revert "FP8 support on NVIDIA (#8631)" 
This reverts commit 2c8e4ea865.
 2025-04-09 12:27:41 +08:00
George Hotz
d1505137ad Revert "move TestOpsFp8s skipTest (#9797)" 
This reverts commit a3aaf92b21.
 2025-04-09 12:27:40 +08:00
George Hotz
14928fecff Revert "fix TF32 tensor core dropped in tc_sm89 (#9798)" 
This reverts commit 7c9a96824f.
 2025-04-09 12:27:39 +08:00
qazal
1ed4eae510 hotfix: don't add shape to SINK viz node (#9800) 2025-04-09 12:04:33 +08:00
chenyu
7c9a96824f fix TF32 tensor core dropped in tc_sm89 (#9798) 
also add `SHOULD_USE_TC=1` to verify TC is applied in simple_matmul
 2025-04-08 23:20:50 -04:00
chenyu
a3aaf92b21 move TestOpsFp8s skipTest (#9797) 
so get_available_devices is not called when running other tests
 2025-04-08 22:44:07 -04:00
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
hooved
5d85765327 types for WebGPU runtime (#9791) 
* add type annotations to ops_webgpu

* rerun CI

* add types to some _run params
 2025-04-08 22:52:17 +03:00
chenyu
4c8582a7ce pipe allow_test_size in _time_program (#9789) 
* pipe allow_test_size in _time_program

it was dropped long time ago and BEAM_ESTIMATE is doing nothing

* revert BEAM_ESTIMATE
 2025-04-08 09:07:40 -04:00
chenyu
8fe83385ec add system json for mi300x mlperf (#9786) 
* add system json for mi300x mlperf

```
python3 -m mlperf_logging.system_desc_checker examples/mlperf/training_submission_v5.0/tinycorp/systems/tinybox_8xMI300X.json training 4.1.0
INFO -   System description checker passed for tinybox 8xMI300X
```

also removed the rocm from tinybox_red since we are not using it

* update mlperf-logging version
 2025-04-08 06:36:44 -04:00
chenyu
4a807ee952 remove duplicated z3-solver in setup.py (#9787) 2025-04-08 06:12:58 -04:00
qazal
21e872df44 remove consts from sched_sink [pr] (#9782) 2025-04-08 16:08:24 +08:00
qazal
f13e9cf2d9 move view_left to grouper.py + tiny reorders [pr] (#9780) 
* move view_left to grouper.py [pr]

* reorder grouper

* test_schedule
 2025-04-08 15:39:28 +08:00
chenyu
7a28133b37 failed test for single softmax backward (#9778) 
getting RecursionError with DONT_GROUP_REDUCES=1
 2025-04-08 02:36:32 -04:00
George Hotz
fefee5d3ab single kernel softmax (#9776) 
* real single kernel softmax

* cleanup

* fix blockend insertion

* add to bert test
 2025-04-08 12:35:48 +08:00
qazal
9963bb51e0 grouper tests cleanups [pr] (#9777) 
* grouper tests cleanups [pr]

* viz

* tuple

* whitespace
 2025-04-08 12:33:11 +08:00
chenyu
4cc7422769 use AM driver in bert mlperf (#9775) 
we should commit to use AM. it's 7ms slower python time now
 2025-04-07 23:40:27 -04:00
George Hotz
db22094d35 hotfix: update softmax fusion test 2025-04-08 11:23:19 +08:00
Francis Lata
f8fe15e64e move BoxCoder to mlperf helpers (#9773) 2025-04-07 20:27:06 -04:00
Eitan Turok
bb7922b95f Vectorize Transcendental Regression Tests (#9753) 
* init test

* cleanup
 2025-04-08 01:27:39 +08:00
chenyu
7c4a739fe4 full script for bert mi300x (#9772) 2025-04-07 11:41:31 -04:00
Sieds Lykles
07d1aefaf4 fast idiv (#9755) 
* fast idiv with tests and fuzzer

* Add todo comment

* Add env variable to toggle fast_idiv

* Move env check

* Add fuzz fast_idiv to ci

---------

Co-authored-by: chenyu <chenyu@fastmail.com>
 2025-04-07 08:32:24 -04:00
nimlgen
fa888ee077 minor test cleanups (#9770) 
* fix test_graph on max

* pcie5
 2025-04-07 15:29:12 +03:00
chenyu
3069ebfad1 use BERT_LAYERS=2 in bert init (#9769) 
save 5 minut scheduling in setup so we can fit more search
 2025-04-07 07:46:37 -04:00
qazal
891322fd51 split into grouper.py (#9768) 
* split into grouper.py

* update tests

* reorder
 2025-04-07 18:40:59 +08:00
qazal
219b8c9e8b return becomes_map in scheduler [pr] (#9766) 
* add a graph_rewrite pass for creating asts [pr]

* disk

* benchmark

* return becomes_map in scheduler

* reorder schedule.py into grouper and linearizer [pr]

* comments
 2025-04-07 17:36:23 +08:00
qazal
6306dea6e2 add a graph_rewrite pass for creating asts [pr] (#9765) 
* add a graph_rewrite pass for creating asts [pr]

* disk

* benchmark
 2025-04-07 16:32:11 +08:00
qazal
07eea567d4 reorder tensor_map and grouper parts [pr] (#9764) 2025-04-07 15:36:13 +08:00
qazal
8ddb1357c0 fix UPat.location after pickle (#9763) 
* fix UPat.location after pickle [pr]

* named upat test
 2025-04-07 15:16:42 +08:00
qazal
4cd27aa0e6 hotfix: viz recenter and unlimited zoom (#9760) 
* hotfix: viz recenter and unlimited zoom

* add shapes to the ast graph

* not for COPY
 2025-04-07 14:38:03 +08:00
chenyu
d0dace4306 update doc for permute to 3d tensor (#9758) 
easier to see if it's permuted to or permuted from
 2025-04-07 00:38:05 -04:00
chenyu
b190d85ad7 benchmark script bert softmax (#9759) 2025-04-07 00:31:18 -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
chenyu
43e4565148 weighted linear in external_benchmark_bert_matmuls (#9757) 
include the linear to get qkv, and permute so that stride matches with the real run
 2025-04-06 23:35:42 -04:00
George Hotz
28e06d2d44 minor cleanups from patternmatcher [pr] (#9756) 2025-04-07 11:28:14 +08:00
qazal
1ce4912770 viz profiler ui (#9664) 
* localhost:8000/prof

* selector + table

* add pid

* on null selection reset filters

* table sort

* charset=utf-8

* clear the rest

* sort by duration

* render table

* format

* nothing in copy thread

* keep starts

* sort back

* less javascript

* diff

* works on firefox
 2025-04-07 00:30:17 +08:00
chenyu
8a585dc5c1 benchmark script for matmuls in bert (#9752) 
2 main matmuls in the bert layers. getting these to be fast makes bert fast
 2025-04-06 19:34:25 +08:00
qazal
139999c6d7 map viz files + query params cleanup [pr] (#9754) 
* map viz files + query params cleanup [pr]

* .width + fix
 2025-04-06 16:20:00 +08:00
Francis Lata
71b8890dd6 use validation dataloader inside retinanet eval (#9747) 2025-04-05 16:46:55 -04:00
nimlgen
5f7c79676f jit: prune independent copies (#9749) 
* jit: prune independent copies

* linter

* check kernel cnt
 2025-04-05 20:50:28 +03:00
nimlgen
c2573b247c jit: rename optimize_weights -> replan_buffers_memory_layout (#9751) 2025-04-05 20:35:15 +03:00
uuuvn
493fb315b1 fix RDNA2 support (#9700) 
linux amdgpu_discovery.c:amdgpu_discovery_set_ip_blocks is a ton of
switch cases with sometimes weird choices like replacing nbio 3.X with
2.3 while nbio 2.5 is somehow nbio 7.0. `import_module` currently just
tries to replace revision and minor with zeroes if there is no exact
match, but that's not enough to cover all that weirdness
 2025-04-05 18:42:47 +03:00
chenyu
5a04f4d4ba revert bert hparams for green and red (#9744) 
did more runs and it's not really better and not worth the change. only useful for BS=1024
 2025-04-05 07:38:01 -04:00
chenyu
407ca54382 symbolic fold double where (#9436) 
* symbolic fold double where

a.where(b.where(c, d), d) -> (a & b).where(c, d). a pattern in optimizer

* test case
 2025-04-05 05:12:17 -04:00
Sieds Lykles
9c2fc695b5 cond.logical_not().where(a,b) -> cond.where(b,a) (#9741) 
* Add rule for negation in where, simplifies arange patterns

* 0 becomes 0.0 again

* Only if cond is bool

* ne is never None

* Add a test

---------

Co-authored-by: chenyu <chenyu@fastmail.com>
 2025-04-04 19:13:32 -04:00