geohot/tinygrad
1
0
Fork 0
forked from tinygrad/tinygrad
Code Pull Requests Actions Activity
12,376 Commits 4 Branches 15 Tags
ccb29d9d3fa1dbfd105e90b6864be5ec6fdeec1f
Commit Graph
61 Commits
Author SHA1 Message Date
George HotzandGitHub ccb29d9d3f Merge branch 'master' into prealloc_bufs 2026-02-20 09:11:44 +08:00
chenyuandGitHub b9744ab62b one more test_gpudims test (#14898) 
failure from the bad simplification attempt
 2026-02-19 18:18:44 -05:00
chenyuandGitHub 9d6cf00be2 fix gpudim bug and test_split_2d_to_3d (#14896) 2026-02-19 16:46:24 -05:00
chenyuandGitHub 2b31823ef9 update test_gpudims to prove bijectivity (#14895) 
* update test_gpudims to prove bijectivity

* one more
 2026-02-19 16:18:59 -05:00
chenyuandGitHub 19ce7a3f7f use z3 to verify gpudims output index (#14894) 
found a bug with z3
 2026-02-19 15:24:38 -05:00
chenyuandGitHub 52f727738b move test_grouped_dims to test/null (#14893) 
it's a pure helper
 2026-02-19 14:50:53 -05:00
chenyuandGitHub 7400362a86 remove UOp.vars [pr] (#14891) 2026-02-19 12:09:39 -05:00
George HotzandGitHub f6c1cf343c new symbolic rule from prealloc_bufs (#14883) 
* new symbolic rule from prealloc_bufs

* optim
 2026-02-19 20:57:30 +08:00
geohot 62d7a760a0 test fixes 2026-02-19 19:46:40 +08:00
geohot f9a569c0fd all tests pass 2026-02-19 18:14:09 +08:00
geohot ed77935635 fixes 2026-02-19 18:11:17 +08:00
geohot 5963393d9b tests 2026-02-19 15:07:47 +08:00
geohot 7c8f5144d8 simpler 2026-02-19 14:57:35 +08:00
George HotzandGitHub 2f0f8b5776 more test relaxations from prealloc_bufs (#14880) 2026-02-19 14:23:28 +08:00
geohot 2f27e93e64 those optimizations aren't supported currently 2026-02-19 13:11:42 +08:00
geohot 6271b3bf33 fix training 2026-02-19 13:08:30 +08:00
geohot e50e5e626e skips 2026-02-19 12:42:41 +08:00
geohot 4850178108 dedup 2026-02-19 12:21:00 +08:00
George HotzandGitHub ec14daf0b7 Merge branch 'master' into prealloc_bufs 2026-02-19 11:37:53 +08:00
George HotzandGitHub ab61c16730 fixes and test relaxations from prealloc_bufs (#14875) 
* fixes and test relaxations from prealloc_bufs

* fix error type and guard _mop

* revert that

* contiguous makes extra/torch_backend/test_kernel_fusion.py fail
 2026-02-19 11:37:25 +08:00
George HotzandGitHub 7d40b84390 Merge branch 'master' into prealloc_bufs 2026-02-19 09:46:03 +08:00
chenyuandGitHub f771de6738 gc.collect() to get the correct GlobalCounters.mem_used in tests (#14868) 
test can be flaky if gc happens in between
 2026-02-18 15:01:23 -05:00
chenyuandGitHub 5746a605ce UOp.axis raises for invalid reshape (#14863) 
reshape is lazy now, so better to raise from the .axis call and not have caller to handle invalid case
 2026-02-18 11:28:56 -05:00
geohot 262984167c tests skips 2026-02-18 19:43:51 +08:00
geohot 628157c944 fix tests 2026-02-18 18:29:27 +08:00
geohot 5446772cdd fix schedule tests 2026-02-18 18:00:41 +08:00
geohot ed202ac5a3 don't check that anymore 2026-02-18 16:55:03 +08:00
George HotzandGitHub ab55e8c6b9 assign should be used as output buffer (#14845) 
* assign should be used as buffer

* late removed

* the fix

* better fix

* backward slice
 2026-02-18 09:37:46 +08:00
chenyuandGitHub 72cf603805 removed if self.buffer.is_allocated() in realized (#14836) 
automatically fixes is_realized issue for empty
 2026-02-17 15:35:56 -05:00
chenyuandGitHub f147791105 update test to reset and test kernel_count directly (#14832) 2026-02-17 11:48:46 -05:00
George HotzandGitHub bc3487d607 VIZ display cleanups (#14811) 
* exclude reshape/expand broadcasts from viz

* limit src lines
 2026-02-17 10:03:08 +08:00
nimlgenandGitHub 9f8afb518c viz: sdma gb/s in graph (#14798) 
* viz: sdma gb/s in graph

* f
 2026-02-16 16:45:06 +03:00
qazalandGitHub db3db476ff viz: add GB/s to SDMA (#14795) 
* work

* better

* fix that

* no decimal
 2026-02-16 20:09:20 +09:00
qazalandGitHub c2be31e75b move Estimates to rewrite rules [pr] (#14782) 
* move Estimates to rewrite rules [pr]

* don't need this cached_property

* tuple

* return
 2026-02-16 12:59:42 +09:00
George HotzandGitHub 0abcb9aac2 move more to mixins (#14780) 
* move more to mixins

* revert

* move some

* do not change

* more

* fix tests

* Revert "more"

This reverts commit d942d59fa4.

* go

* work

* more

* work

* guard

* base
 2026-02-16 11:35:00 +08:00
George HotzandGitHub 9759fd6193 dtype mixin (#14763) 
* dtype mixin

* dtype mixin methods
 2026-02-15 16:03:48 +08:00
geohot 32980c74d1 hotfix: skip flaky tests, looped many times on tinymac3 2026-02-15 07:46:29 +08:00
chenyuandGitHub 043f5dbfa0 fix write-after-read tracking (#14754) 
AFTER-AFTER was silently dropped, which breaks write-after-read
 2026-02-14 17:23:05 -05:00
chenyuandGitHub 0ce4a55dad clean up test_setitem_slice (#14750) 
moved to test_setitem_schedule, and use contiguous zeros as scheduler handles empty differently now
 2026-02-14 14:29:16 -05:00
nimlgenandGitHub e1a18dadae fix devices for copies (#14747) 
* fix devices for copies

* add test
 2026-02-14 17:39:41 +03:00
George HotzandGitHub c0fe78f73b BUG: metadata is lost with partial assign (#14732) 2026-02-13 21:35:21 +08:00
chenyuandGitHub 50cb40be88 clean up test/null/test_indexing.py (#14720) 2026-02-12 22:36:53 -05:00
qazalandGitHub 5b624b5e93 viz: better error message for out of range timestamps (#14722) 
* test_timestamp_out_of_range

* rel_ts helper

* linter
 2026-02-13 12:13:40 +09:00
chenyuandGitHub 86352988d8 update test_uops_stats for setitem (#14710) 
realize both full tensor and the slice should not add to global_mem
 2026-02-12 12:26:13 -05:00
chenyuandGitHub 56caf6a3a2 fix Estimate.from_uops for sliced access (#14695) 
"assume all DEFINE_GLOBAL memory is accessed" is wrong for partial load. get accessed accumulated from INDEX, then cap at full size. now mem_est never exceeds lds_est
 2026-02-12 11:18:07 -05:00
chenyuandGitHub 8551fa50d3 support bitcast in sym_infer (#14708) 
fixed `DEBUG=2 DEV=WEBGPU python -m pytest test/backend/test_tensor_variable.py::TestTensorVariable::test_symbolic_pad`
 2026-02-12 10:21:05 -05:00
chenyuandGitHub 557134e1c7 model/test fix that failed with WEBGPU=1 DEBUG=2 (#14706) 2026-02-12 09:08:16 -05:00
nimlgenandGitHub 14a1991da6 viz: sort tracks in timeline (#14591) 
* viz: sort devices in timeline

* fix

* rev

* upd

* skip
 2026-02-12 10:51:41 +03:00
George HotzandGitHub c331798201 move tests to test/backend (#14691) 
* move tests to test/backend

* fix imports

* fix CI

* revert that one

* Fix formatting in README for test command
 2026-02-12 11:09:44 +08:00
George HotzandGitHub 8dc46dde07 everything has dtype.long now (#14661) 
* everything has dtype.long now

* int64/uint64 are everywhere now

* that doesn't work
 2026-02-10 15:08:50 +08:00