github/tinygrad
1
1
Fork 0
mirror of https://github.com/tinygrad/tinygrad.git synced 2026-02-12 15:45:27 -05:00
Code Issues Packages Projects Releases Wiki Activity
7,557 Commits 221 Branches 14 Tags
5842ee56c6837a6e2c408e0c13db9efb30ccd006
Commit Graph

250 Commits

Author SHA1 Message Date
chenyu
5842ee56c6 raise if attn_mask is set when is_causal=True in sdpa [pr] (#8675) 
matches torch, also fixed incorrect usage in tests
 2025-01-19 12:55:04 -05:00
qazal
2faf8774fe replace DEVICE of CONST after copy folding (#8673) 2025-01-19 11:33:39 -05:00
qazal
d957a4f108 add tests for div buffer collapsing in the scheduler [pr] (#8671) 
* add tests for mul/div buffer collapsing in the scheduler [pr]

* lint

* merge with test_linearizer's version of this

* 4*3
 2025-01-18 14:15:29 -05:00
qazal
2b7db9b45d delete unused cast/bitcast lines from ops.py [pr] (#8651) 
* move cast and bitcast out

* more deletion of bitcast arg

* fix test_bitcast_fuses

* update tests

* work
 2025-01-17 03:04:18 -05:00
qazal
81a84aa85a remove is_unrealized_unmasked_const [pr] (#8644) 2025-01-16 05:27:47 -05:00
qazal
a1f70ce7d0 only use BUFFER_VIEW in disk [pr] (#8629) 
* only use BUFFER_VIEW in disk [pr]

* delete can_view

* BUFFER_VIEW op on DISK

* remove that allow_buffer_view=False

* notes

* bitcast is a low-level op too

* this passes on AMD and LLVM
 2025-01-15 12:34:15 -05:00
George Hotz
504ad08e73 hotfix: add test_example_matmul_same 2025-01-14 19:03:17 -08:00
George Hotz
bfbe81df71 remove cast before view (#8613) 
* remove cast before view

* greener

* indexing

* that passes too

* openpilot too

* ack

---------

Co-authored-by: qazal <qazal.software@gmail.com>
 2025-01-14 15:04:58 -05:00
qazal
ae2229d727 assert kernel buffer limit at compile time [pr] (#8595) 
* remove the BUF_LIMIT assert

* skip the base one
 2025-01-13 16:32:07 -05:00
qazal
7562cc0399 better test for reduce swizzle + don't use double dtype [pr] (#8586) 
* better test_permute_rewrite

* use float32
 2025-01-13 05:02:21 -05:00
qazal
cff1ee9038 add SINK folding from the tensor_map branch [pr] (#8562) 
* delete is_constant from the scheduler

* add sink folding

* always give BUFFER uops Buffers [pr]

* spec for view, var (bind) and const

* add test_buffer_only_after_realize

* work

* 3 lines

* more work
 2025-01-12 03:39:34 -05:00
qazal
87cbff3ac0 always give BUFFER uops Buffers [pr] (#8572) 
* always give BUFFER uops Buffers [pr]

* add test_buffer_only_after_realize
 2025-01-11 23:17:09 +02:00
chenyu
d09897c2aa allow double copy [pr] (#8559) 
fixed ring allreduce pattern and recovered most of the bert step time regression (10% faster), will double check all benchmark
 2025-01-10 18:21:01 -05:00
qazal
2fd068ffc0 delete empty op (#8544) 
* simple delete EMPTY op

* there's no schedule for empty
 2025-01-09 14:10:15 -05:00
qazal
f6eb0574f2 start tests for putting the tensor graph in a single kernel [pr] (#8542) 
* start tests for putting the tensor graph in a single kernel [pr]

* parallel actually

* better view_left test

* test a softmax

* put all that in sym
 2025-01-09 13:33:21 -05:00
qazal
947de23cac add VIEW(DEVICE) to tensor variable [pr] (#8529) 
* add VIEW(DEVICE) to tensor variable [pr]

* bind 2

* restrict shapetracker

* move var and bind closer

* one less line
 2025-01-08 01:39:42 -05:00
qazal
b22494b710 restrict tensor const ShapeTracker in spec [pr] (#8447) 
* restrict tensor const ShapeTracker in spec [pr]

* pass sink srcs

* reject if any of the specs disagree

* deceive mypy

* viz

* default to float

* just check the view

* create_schedule is gone

* test_verify_arg is flaky
 2025-01-07 19:05:11 -05:00
qazal
0e97f807e0 test fixup prereqs for delete_buffer_view [pr] (#8523) 2025-01-07 11:52:18 +02:00
qazal
ed618a72e7 do not use subbuffer for bitcast (#8514) 
* do not use subbuffer for bitcast

* edit that test

* explicit test for ptx

* ptx
 2025-01-06 18:40:46 +02:00
qazal
ed121d235c spec for CAST_BEFORE_VIEW=1 [pr] (#8512) 2025-01-06 10:43:58 +02:00
qazal
eb7df92136 dedup COPY UOp [pr] (#8506) 2025-01-06 10:37:20 +02:00
qazal
bd4d7dc4eb return becomes_map from the scheduler (#8483) 
* return becomes_map from the scheduler

* fix test_schedule

* fix abstractions2

* s/becomes/becomes_map
 2025-01-03 22:47:21 +08:00
qazal
0d33391038 delete unused allow_buffer_view=True arg from bitcast [pr] (#8462) 2025-01-03 22:20:46 +08:00
qazal
08c9d980dc use const_like in uop zero folding [pr] (#8470) 2025-01-03 01:05:09 +08:00
qazal
f2bee34197 tests for symbolic_simple failing tensor const spec [pr] (#8469) 
* tests for symbolic_simple failing tensor const spec [pr]

* mul is correct
 2025-01-02 19:13:16 +08:00
qazal
c7ec0ab674 delete unused View lt support (2) (#8451) 
* delete lt on view (2)

* the scheduler uses symbolic_simple
 2024-12-31 07:01:25 +08:00
qazal
866dfa1f23 create_schedule([x.lazydata]) -> x.schedule() in tests (#8449) 2024-12-31 03:15:52 +08:00
qazal
7499139239 scheduler renames from the buffer_shape branch [pr] (#8444) 
* scheduler refactors and renames from the buffer_shape branch [pr]

* all unmasked sts are allowed here

* only renames
 2024-12-30 16:33:38 +08:00
George Hotz
b71c51191b tests from remove uop mutability [pr] (#8442) 
* tests from remove uop mutability [pr]

* more test fix

* simpler test fix

* remove that
 2024-12-29 12:14:10 -05:00
qazal
34987a03af const copy folding spec + multi.py behavior [pr] (#8436) 
* const copy folding spec + multi behavior [pr]

* copy from clang, move multi test
 2024-12-29 23:12:13 +08:00
qazal
a44cd1e6f7 add collapse_view to the scheduler [pr] (#8440) 2024-12-29 21:30:29 +08:00
qazal
b5820a5209 deletions from an ops.py "instant rule" audit [pr] (#8424) 
* UOp.st cleanup 2 [pr]

* deletions from an ops.py instant rule audit [pr]

* note
 2024-12-27 00:49:04 +08:00
qazal
9defbc7d54 add symbolic_simple to the scheduler [pr] (#8419) 2024-12-26 20:05:08 +08:00
qazal
313bdfa43f Add View lt support back [pr] (#8407) 
* Revert "remove unused View.t and lt [pr] (#8374)"

This reverts commit 8fdcb60461.

* green test_masked_const_elementwise
 2024-12-26 01:09:59 +08:00
qazal
4cbe5919d6 tensor uops symbolic folding spec [pr] (#8406) 2024-12-26 00:26:41 +08:00
qazal
3273972f44 delete is_unrealized_const, it's just CONST [pr] (#8390) 2024-12-24 16:46:12 +08:00
qazal
3a556a7e8b fully local tensor const representation: CONST(VIEW(DEVICE)) [pr] (#8389) 2024-12-24 16:15:56 +08:00
qazal
514a6740e4 Revert "CONST(VIEW(DEVICE)) (#8365)" (#8372) 
This reverts commit 83284985f0.
 2024-12-22 04:44:34 +02:00
qazal
83284985f0 CONST(VIEW(DEVICE)) (#8365) 2024-12-22 04:18:35 +02:00
qazal
88bc51385c scheduler: don't trade complexity for speed (#8370) 
* scheduler: don't trade complexity for speed

* don't need is_scheduled

* make those tests real world

* graph_rewrite dedup
 2024-12-22 03:30:51 +02:00
qazal
72aa38aa3b BIND in tensor_uop_spec + cleanups [pr] (#8363) 
* Ops.BIND pattern in tensor_uop_spec + cleanups [pr]

* use metaops there
 2024-12-21 21:26:47 +08:00
qazal
2649e87546 delete the fake buffer from const (#8355) 
* delete the fake buffer from const

* fix test_sink_childless_const_alt

* it should be CONST(VIEW(DEVICE))
 2024-12-21 04:20:28 +08:00
qazal
8e266091fb tensor const spec [pr] (#8331) 2024-12-19 22:41:30 +08:00
qazal
fddaeb6344 scheduler deduping spec and asserts [pr] (#8307) 
Co-authored-by: George Hotz <72895+geohot@users.noreply.github.com>
 2024-12-18 09:21:41 -08:00
George Hotz
801e199196 change buffer to not be pointer [pr] (#8302) 2024-12-17 16:47:51 -08:00
George Hotz
6d83a96440 retry: use movement ops [pr] (#8225) 
* Revert "Revert "use movement ops [pr] (#8222)" (#8224)"

This reverts commit da19c37f0a.

* fix cast before view
 2024-12-13 15:14:26 -08:00
George Hotz
da19c37f0a Revert "use movement ops [pr] (#8222)" (#8224) 
This reverts commit 0d26c970ba.
 2024-12-13 14:10:47 -08:00
George Hotz
0d26c970ba use movement ops [pr] (#8222) 
* use movement ops [pr]

* test indexing
 2024-12-13 14:06:01 -08:00
George Hotz
dbe549e462 rename expand to unroll [pr] (#8218) 2024-12-13 11:41:52 -08:00
George Hotz
8a04a3a77a rename LazyBuffer -> UOp [pr] (#8169) 
* rename LazyBuffer -> UOp [pr]

* fix docs
 2024-12-11 16:15:52 -08:00