geohot
59bfab8a9b
sym
2025-08-13 17:49:54 -07:00
geohot
b5d7d339f4
no range arg
2025-08-13 17:43:17 -07:00
George Hotz and GitHub
b7c195bf7e
Merge branch 'master' into no_merge_views
2025-08-13 16:21:41 -07:00
chenyu and GitHub
4fe19eec72
Ops.TRUNC ( #11659 )
2025-08-13 18:40:48 -04:00
qazal and GitHub
eb10a9c76a
viz: always left align timeline values ( #11658 )
2025-08-13 23:55:28 +03:00
George Hotz and GitHub
8592fba874
Merge branch 'master' into no_merge_views
2025-08-13 12:46:52 -07:00
George Hotz and GitHub
22bdf48cdd
render ranges in viz, name gbufs with sizes. changes from rangeify ( #11656 )
...
* render ranges in viz, name gbufs with sizes. changes from rangeify
* fix unit test dtypes
2025-08-13 12:46:16 -07:00
George Hotz and GitHub
9b4da590bb
remove need for cast_vec ( #11653 )
...
* remove need for cast_vec
* fix amdllvm
2025-08-13 12:09:47 -07:00
geohot
10ffd7e17b
simpler
2025-08-13 11:42:42 -07:00
e2873a3a41
[bounty] Muon optim ( #11414 )
...
* newton schulz
* add muon + move newton schulz to tensor
* compact newton schulz
* better tests
* cleanup
* add comments for muon
* cleanup
* add export with tests
* match muon optim with test optim
* cleanup
* unsed import
* correct comment
* whitespace
* move export
* muon test fix
* match reference impl + tests
* remove export by moving muon device
* add credit
* cleanup
* remove print
* spacing
* spacing
* comma
* cleanup
* removal
* fix tests + optim momentum
* consistent is not/ not
* more consistency
* fix test
* cleanup
* fix the nones
* remove comment
* cast
* comment
* comment
* muon teeny test
* muon flag beautiful mnist
* set steps
* steps as hyperparam
* match default test steps
* name
* large cleanup
* dont care about steps
* nesterov false default
* match each other impl
* steps
* switch nest
* swap defaults
* update docstring
* add no nesterov test
* ban fuse_optim
* prints
* classical momentum
* alternative condition
* recon
* pre + post wd
* false default
* detach
* signature changes
* context
* swap order
* big cleanup
* 0 step instead
* parity
* remove fuse
* remove fused
* better paper
* assert message
* correct shape check + eps
* multidim
* add eps
* cleanup
* correct assert message
* lint
* better tests
* naming
* ns_steps,ns_params
* update docstring
* docstring
* match sgd and muon together
* sandwich
* add back fused
* parity
---------
Co-authored-by: George Hotz <[email protected]
2025-08-13 14:27:55 -04:00
chenyu and GitHub
94e6d84e32
rewrite Tensor.round to not use cast int ( #11654 )
2025-08-13 13:51:08 -04:00
geohot
5489be812c
random works
2025-08-13 09:47:02 -07:00
geohot
e3d8185ba4
ignore that
2025-08-13 09:43:08 -07:00
George Hotz and GitHub
cbf85fbfd0
Merge branch 'master' into no_merge_views
2025-08-13 09:40:44 -07:00
George Hotz and GitHub
d2521d828a
transcendental+idiv+threefry are uop decompositions ( #11636 )
...
* transcendental+idiv+threefry are uop decompositions [pr]
* threefry decomp
* fix randomness tests
* fix webgpu
* unneeded now
* fix
* move prematcher
* all cast should probably be cast_vec
2025-08-13 09:37:12 -07:00
geohotstan and GitHub
cf7224ce3e
fully lint onnx.py ( #11647 )
...
* mypy
* ruff ruff ruff
2025-08-13 08:22:06 -07:00
geohotstan and GitHub
925555b62a
Fix onnx Domain bug ( #11650 )
2025-08-13 08:20:50 -07:00
Sieds Lykles and GitHub
67df617fe1
add launch bounds to ptx ( #11646 )
2025-08-13 13:05:39 +02:00
qazal and GitHub
88f95e9f59
viz: minor fixups for firefox ( #11645 )
...
* fix circle attr
* set fill color
2025-08-13 12:59:28 +03:00
qazal and GitHub
6f88eac0fc
viz: refactor node and edge tagging ( #11644 )
2025-08-13 12:41:01 +03:00
qazal and GitHub
8140bf9778
viz: create layout once ( #11643 )
...
* start
* work
* works
* diff cleanup
2025-08-13 09:24:58 +03:00
chenyu and GitHub
3fb79bb43a
minor onnx cleanups ( #11642 )
2025-08-13 01:05:19 -04:00
chenyu and GitHub
e9e5a08a04
simplify onnx cubic ( #11641 )
...
we can drop the double where and abs since we know which ranges the inputs map into
2025-08-12 19:57:31 -04:00
George Hotz and GitHub
18cdbec447
split decompositions pass ( #11638 )
...
* split decompositions pass
* fix ptx
* pack load store early
* restore that
2025-08-12 12:56:05 -07:00
chenyu and GitHub
0d8a0d7a96
update test_multi_const_folding_tensor to include pow ( #11635 )
...
pow folds now
2025-08-12 13:35:37 -04:00
Sieds Lykles and GitHub
4d6e407eb0
Extend fast_idiv to negative ints ( #11632 )
...
* fast idiv for signed ints
* Add rule and test
* fix tests
* redo fuzz_fast_idiv to do negative ints as well
* adjust comments
* remove unused imports
2025-08-12 19:34:49 +02:00
qazal and GitHub
17adbe86d8
hotfix: do not default to capturing args in track_rewrites ( #11634 )
2025-08-12 20:01:24 +03:00
ad9dec25b3
combine onnx parser and onnx ( #11485 )
...
* start
* more
* fix onnx_runner test
* pass
* patch for disk and add domains from huggingface
* simpler docs
* revert domain changes
* rerun ci
* revert onnx ops test change
* add fix from strenum stuff
* correct way
* revert correct way to leave the fix for another PR
* test segfault
* Revert "test segfault"
This reverts commit 4e1aaf41e756fc5f03e7[email protected]
2025-08-12 12:56:39 -04:00
Sieds Lykles and GitHub
4c3982c44e
Take sign out of mod ( #11631 )
...
* Add rule and test
* fix tests
2025-08-12 18:44:36 +02:00
qazal and GitHub
e28605e324
rename profile point event fields [pr] ( #11633 )
2025-08-12 19:11:21 +03:00
nimlgen and GitHub
8a7be0a747
metal: workaround for transfers sync issue ( #11622 )
...
* metal: workaround for transfers sync issue
* metal tracsfer sync is broken
* hm
* rm it?
* keep it
2025-08-12 16:16:34 +03:00
qazal and GitHub
efe8b5611d
move ProfilePointEvent out of device.py [pr] ( #11630 )
...
Generic profiling events exist in helpers so they can be imported from
everywhere in tinygrad.
2025-08-12 09:58:32 +03:00
chenyu and GitHub
0d7075f2de
assign should broadcast input tensor ( #11629 )
...
fixed test_assign_broadcast
2025-08-11 23:36:35 -04:00
Joshua Kissoon and GitHub
c44760c89d
torch backend: fix arange, add linalg.cross, add tests ( #11628 )
2025-08-11 23:34:41 -04:00
geohot
11d65cb002
test_gemm works
2025-08-11 18:58:40 -07:00
geohot
5f0816ef69
simpler
2025-08-11 18:41:32 -07:00
George Hotz and GitHub
b8b28e1135
Merge branch 'master' into no_merge_views
2025-08-11 18:29:15 -07:00
George Hotz and GitHub
ca41b5e38b
skip_0 in graph rewrite [pr] ( #11627 )
...
* skip_0 in graph rewrite [pr]
* no track_rewrites on test
* use dict instead of set
2025-08-11 18:29:04 -07:00
Sardor and GitHub
ca7a641442
fix bugs at examples/yolov3.py ( #11614 )
...
* Update load_weight. Give valid model url
* Fix bug in iou function
2025-08-11 21:14:47 -04:00
chenyu and GitHub
0c97d6de1b
don't round pow output for int pow int ( #11625 )
...
also added atol=0 and big pows for the tests
2025-08-11 20:57:47 -04:00
geohot
9d46bc2939
endrange
2025-08-11 17:19:02 -07:00
chenyu and GitHub
d623f6d850
support int Tensor pow to const non-negative int ( #11624 )
...
matches torch
2025-08-11 19:50:19 -04:00
geohot
2b7957e765
map_expand
2025-08-11 15:22:56 -07:00
geohot
4102e46370
cache has issues
2025-08-11 14:35:23 -07:00
chenyu and GitHub
857a830dcc
fix test_arange_float_step ( #11623 )
2025-08-11 16:58:42 -04:00
George Hotz and GitHub
6da4784c66
Merge branch 'master' into no_merge_views
2025-08-11 13:23:14 -07:00
chenyu and GitHub
0806677b51
rewrite sort idx ( #11613 )
2025-08-11 16:20:56 -04:00
George Hotz and GitHub
700c11597b
switch contextvars.ContextVar to _ContextVar ( #11621 )
2025-08-11 12:20:09 -07:00
ae0c3cfff6
change clang -march flag to -mcpu on arm ( #10970 )
...
Co-authored-by: wozeparrot <[email protected]
2025-08-11 13:38:48 -04:00
geohot
2feeb8c8a6
cleanups
2025-08-11 08:57:30 -07:00
geohot
