George Hotz
ccd753e1aa
set testpath on pytest
2025-09-15 14:29:30 +08:00
George Hotz
ae0edc8a67
renumber ranges ( #12182 )
...
* enable rangeify const folding
* renumber ranges for kernel deduping
2025-09-15 13:03:39 +08:00
hooved
e1fef895b1
don't hardcode weights path ( #12171 )
2025-09-15 00:33:47 -04:00
hooved
3a9db08b49
download data and ckpts for sd train/eval ( #12170 )
2025-09-15 00:31:45 -04:00
chenyu
bdb3afd566
failed test case for symbolic pad ( #12179 )
2025-09-15 00:25:21 -04:00
George Hotz
9fcc87761e
enable rangeify const folding ( #12181 )
2025-09-15 12:02:19 +08:00
George Hotz
1353250b6c
tags on bufferize are the tensor tags ( #12180 )
2025-09-15 11:46:03 +08:00
George Hotz
60d7db093e
delete bufferized consts + output noops ( #12163 )
...
* bring const folding to rangeify
* comment that
2025-09-15 11:07:44 +08:00
qazal
525c20dc7e
viz: remove unused runtime_stats feature ( #12177 )
2025-09-15 02:53:05 +03:00
qazal
75ff9b7a9a
viz: add buffer lifetime to tooltip ( #12175 )
2025-09-15 02:33:50 +03:00
chenyu
15b166ce6d
bump test_module_runs to 30 seconds ( #12174 )
...
25 seconds sometimes
2025-09-14 16:48:40 -04:00
ttomsa
943236ef74
move cast pat out of symbolic_simple ( #11945 )
...
* move pat
* move it here
* rm extra check
---------
Co-authored-by: Sieds Lykles <93992551+S-Lykles@users.noreply.github.com >
2025-09-14 21:39:48 +02:00
Steven Shi
25b1bc8eff
added top k sampling to examples/mamba ( #12061 )
2025-09-14 15:27:34 -04:00
Shun Usami
34a05b31fe
Fix advanced tensor indexing setitem ( #12128 )
...
* Add failure test case for advanced tensor indexing setitem
* Fix advanced tensor indexing setitem when permuted
* Reduce line count
* Revert unnecessary change
* Combine two lines into one
2025-09-14 15:22:40 -04:00
chenyu
d09c0f28c5
increase test_module_runs ( #12173 )
...
timed out on ci windows llvm
2025-09-14 15:19:21 -04:00
chenyu
12a910f1d2
update torch 2.8 ( #12172 )
...
support _reshape_alias. something is wrong with one case of unfold
2025-09-14 15:19:03 -04:00
chenyu
98ecab7563
remove ml_dtypes ( #12169 )
2025-09-14 14:20:05 -04:00
qazal
02054b53fe
remove tests that pre date the uop spec ( #12168 )
...
* remove tests that pre date the uop spec
* const src
* for RANGEIFY=1
* update with bind
* remove import
2025-09-14 18:47:42 +03:00
qazal
1591e4f66b
update outbufs selection in test_linearizer [pr] ( #12166 )
2025-09-14 13:46:49 +03:00
nimlgen
d1ae30f7ef
hcq: do not spam with errors in -m device ( #12150 )
...
* hcq: do not spam with errors in -m device
* um?
* um?
* nn
* helps?
* um?
* no gc?
* fix
2025-09-14 10:56:59 +03:00
George Hotz
d5bc27797b
fix some multitensor on rangeify ( #12162 )
...
* fix some multitensor on rangeify
* rangeify multi hacks
* copy on const
2025-09-14 14:31:57 +08:00
Meng Zhuo
4b7904eca9
add cpu support for riscv64 ( #12136 )
2025-09-14 11:40:58 +08:00
George Hotz
bcafa72b7f
use tags instead of graph_rewrite_map in rangeify ( #12110 )
...
* use tags instead of graph_rewrite_map in rangeify
* new style, add realize
* metadata works
* simple failure
* fix
* loops
* stuff becomes a NOOP when you remove it
* stuff becomes a NOOP when you remove it
* tags on bufferize
* bmnist works
* locals don't work
* shippable
* fix some tests
* simpler map_realize
* remove const hack
* debuggable test
* broke
* assign test
* straight up bug
* wooo it passes
* sink shouldn't be there
* fix ops
* bmnist
* kv cache ish
* Set RANGEIFY context variable to 0
* should work normal
* better
* types
* hacks to fix test_symbolic
* pm_add_buffers
* tests should pass
2025-09-14 11:39:01 +08:00
chenyu
d2316ba91a
don't validate output in sdxl with fakeweights ( #12160 )
...
NULL backend passed validation before because both desired and actual went through NULL backend
2025-09-13 21:47:51 -04:00
nimlgen
b1d1816f43
device: fix envvars ( #12159 )
2025-09-13 23:38:09 +03:00
nimlgen
19d9d29b7e
device: compilers in tinygrad.device ( #12151 )
...
* hcq: do not spam with errors in -m device
* -m tinygrad p2
* fix
* ugh
* comp in ckey
* fix
* one more
* print defaults
* xx
2025-09-13 21:45:29 +03:00
qazal
6410dcb7c2
viz: less verbose render loop ( #12158 )
...
* define visible once
* move y offsets to one place
2025-09-13 19:04:37 +03:00
nimlgen
92df52d79a
make method_cache account for compiler ( #12156 )
...
* make method_cache account for compiler
* sorry
2025-09-13 17:00:11 +03:00
chenyu
0c392089d9
update mypy ( #12155 )
2025-09-13 09:48:38 -04:00
qazal
fbca6183ad
do not launch BEAM when opts_to_apply exists [pr] ( #12152 )
2025-09-13 14:57:46 +03:00
George Hotz
b2a95d32bb
check clSetKernelArg ( #12149 )
2025-09-13 17:24:55 +08:00
George Hotz
0695e322a8
fix android cpu device ( #12148 )
2025-09-13 15:42:04 +08:00
Sieds Lykles
e3a3764917
delete fold_unrolled_divs ( #12146 )
2025-09-13 03:09:36 +02:00
Sieds Lykles
51ed6e94b2
AxisType __repr__ method ( #12145 )
2025-09-13 01:15:38 +02:00
Sieds Lykles
0757a9a819
add pytest-timeout of 3 min per item ( #12144 )
...
* add pytest-timeout with timeout of 3 min
* func_only
2025-09-13 00:48:41 +02:00
Sieds Lykles
2fc0bd150b
Arange overflow raises error and one_hot upcast ( #11975 )
...
* add error
* to_dtype
* shorten line
* add test
* upcast one hot dim im overflows
2025-09-13 00:18:25 +02:00
chenyu
aac3dceaf6
merge two PYTHON backend ci job ( #12143 )
...
* merge two PYTHON backend ci job
and mark anything that takes > 10 in test_ops slow
* two more
2025-09-12 17:36:46 -04:00
ttomsa
a12d0933c1
fix vec dtype in fast idiv ( #12080 )
...
* fix
* add vec dtypes to fuzzer
* add vec=False
---------
Co-authored-by: Sieds Lykles <93992551+S-Lykles@users.noreply.github.com >
2025-09-12 23:00:43 +02:00
chenyu
25091951ba
update test/models ( #12142 )
...
minor fix and run more stuff in tinygrad for speed
2025-09-12 16:43:28 -04:00
Sieds Lykles
62376c8b2b
update store load noop pattern to use Invalid ( #12141 )
...
* update pattern
* add test
2025-09-12 22:25:53 +02:00
chenyu
647965fb09
test_train cleanup ( #12140 )
...
* test_train cleanup
remove skipIf due to buffer sizes, runs locally
* those are slow
2025-09-12 13:21:30 -04:00
chenyu
0fad07c684
viz serve default path ( #12139 )
...
`python tinygrad/viz/serve.py` shows last session instead of an empty page
2025-09-12 18:32:44 +03:00
nimlgen
81e33b8439
system: cpu memory mappings are uncached ( #12137 )
...
* system: cpu memory mappings is uncached
* adm amd
2025-09-12 13:28:25 +03:00
qazal
68b0ad05a4
viz: format tuple tags ( #12135 )
...
* viz: format tuple tags
* use python repr
2025-09-12 11:36:53 +03:00
qazal
e80c8a7548
merge TestIndexing with TestSchedule + remove duplicate tests ( #12134 )
...
* merge TestIndexing with TestSchedule
* remove the arange_copy tests
* no FUSE_ARANGE import
2025-09-12 10:35:14 +03:00
Sieds Lykles
b5a3b8de20
remove where on gated load if gates are the same ( #12129 )
...
* add rules
* add tests
2025-09-12 06:52:35 +02:00
George Hotz
a2f502b89e
fix rangeify=1 ops on GPU ( #12130 )
2025-09-12 11:17:37 +08:00
George Hotz
0766616962
isolate the const hacks in the old kernelize ( #12126 )
...
* isolate the const hacks in the old kernelize
* if rangeify, don't waste time
2025-09-12 08:35:35 +08:00
Sieds Lykles
1f3950a484
Invalid idx ( #12067 )
...
* merge index_dtype_3
* new lowering with Invalid idx
* remove that dtype from range
* finish merge
* annotate better
* indentation
* dont need that anymore
* always process replay for openpilot
* more uop_given_valid for idx
* valid past index_child
* fix bug preventing load getting an alt value
* add track_match_stats back in in shapetracker and remove cache
* get_valid_idx -> get_valid and get_idx
* fix heuristics with new idx
* split line
* fix typo
* fix signature
* dont skip idx if stride is 0
the idx may still be invalid
* lower const with new valid
* delete to_indexed_uops
* update shapetracker test
* delete axis_is_masked
* add cache back
* move around comment
* fix get_valid bug
* move invalid fold to symbolic so its earlier
* cleanup
* update applying padto to new idx
* add unit tests
* cleanup
* fold line
* improve spec
* dont try to render Invalid as a float
* more consistent invalid index
* update some tests
* Fold index with true cond
* skip test
* vconst min max if Invalid in arg
* fix signature of UOp.const
* add test for min/max of Invalid CONST/VCONST
* add InvalidType to as_const signature
* is Invalid to isinstance
* Add InvalidType to ConstLike
* index gate is a where gate
* make that a metaclass
* fix heurisics for new idx
* mypy happy
2025-09-12 01:42:02 +02:00
chenyu
544eb2c402
clean up test_scatter_reduce ( #12125 )
2025-09-11 16:36:58 -04:00
