George Hotz
1a780f2851
error
2025-10-08 19:37:28 +08:00
George Hotz
42210f5487
failing
2025-10-08 19:36:39 +08:00
George Hotz
23783681ca
Merge branch 'master' into rtoposort
2025-10-08 19:15:38 +08:00
George Hotz
9759899cb7
actually make the file readable
2025-10-08 19:14:02 +08:00
qazal
c5a1f9f5f9
no ShapeTrackers in multi.py ( #12521 )
...
* switch multi to all movement ops
* inline dvars
2025-10-08 14:04:05 +03:00
George Hotz
29509a1a57
Merge branch 'master' into rtoposort
2025-10-08 18:48:17 +08:00
George Hotz
8c3242bb45
disable failing test
2025-10-08 18:47:27 +08:00
George Hotz
b264772ae4
touch up tests + add comments
2025-10-08 18:38:48 +08:00
chenyu
ee0382ad99
remove ShapeTracker.invert ( #12520 )
2025-10-08 18:37:34 +08:00
George Hotz
3f927e7bb3
move to indexing.py
2025-10-08 18:32:21 +08:00
George Hotz
e131a5ef0f
mstack/mselect no hacks
2025-10-08 18:20:36 +08:00
chenyu
d5058427ea
remove ShapeTracker.real_size ( #12519 )
2025-10-08 06:15:29 -04:00
George Hotz
fc01a7cc15
tests
2025-10-08 18:02:58 +08:00
qazal
6f26603f06
delete swizzler.py ( #12518 )
...
* delete swizzler
* remove merge_views tests
* don't need rewrites_for_views
* apply_rewrites
2025-10-08 13:02:34 +03:00
George Hotz
04b7b68242
ending ranges fix
2025-10-08 18:00:21 +08:00
George Hotz
f09f46d028
put in rangeify map
2025-10-08 17:32:40 +08:00
qazal
7e0b14243e
delete grouper and kernelize ( #12517 )
...
* delete grouper and kernelize
* +sys.setrecursionlimit
2025-10-08 12:27:26 +03:00
George Hotz
9e884403e9
don't delete those shape ops
2025-10-08 17:20:10 +08:00
chenyu
942022c309
smaller LLAMA_LAYER in Test llama 3 training ( #12516 )
...
very slow now
2025-10-08 05:10:51 -04:00
George Hotz
cd8942cc77
tests passing
2025-10-08 17:06:43 +08:00
chenyu
e701106a64
remove FUSE_ARANGE ( #12511 )
...
it was the default already
2025-10-08 04:54:07 -04:00
qazal
291a19650b
move Kernel dataclass to rangeify ( #12510 )
2025-10-08 11:30:06 +03:00
qazal
ad49f8148b
switch process_replay to rangeify ( #12509 )
2025-10-08 11:26:43 +03:00
chenyu
da1f46ff3f
remove RANGEIFY specific test jobs ( #12507 )
2025-10-08 04:12:04 -04:00
George Hotz
e3f073b957
Merge branch 'master' into rtoposort
2025-10-08 16:04:43 +08:00
George Hotz
91d60d83e0
FAST
2025-10-08 16:04:33 +08:00
George Hotz
1e567a5cf8
make RANGEIFY=1 the default ( #12161 )
...
Co-authored-by: chenyu <chenyu@fastmail.com >
Co-authored-by: Sieds Lykles <93992551+S-Lykles@users.noreply.github.com >
Co-authored-by: qazal <77887910+Qazalin@users.noreply.github.com >
2025-10-08 03:46:09 -04:00
George Hotz
c9ab0a0e26
pad fix
2025-10-08 15:31:40 +08:00
nimlgen
9e7103647d
amd: rename cmd_id to sqtt_next_cmd_id ( #12503 )
...
* amd: rename cmd_id to sqtt_next_cmd_id
* and typo
2025-10-08 15:16:19 +08:00
George Hotz
b4eb5fcac5
Merge branch 'master' into rtoposort
2025-10-08 15:14:43 +08:00
George Hotz
985c0c20a9
progress
2025-10-08 14:33:06 +08:00
nimlgen
4a756a37d8
amd: support rocm7 ( #12502 )
...
* amd: support rocm7
* mock
2025-10-08 14:30:39 +08:00
George Hotz
5042e0b5af
should work
2025-10-08 14:06:51 +08:00
George Hotz
53eb2af4ce
fast rangeify works for mnist
2025-10-08 12:58:40 +08:00
qazal
60b6dca5ba
update some tests instead of expect_rangeify_fails ( #12500 )
...
* update test_clone_doesnt_dedup to use base
* new_flat_buffer passes
* fix test_reorder_expand
* remove the view stuff
* remove that test, we don't want this view const behavior
* test_setitem_becomes_subbuffer is good
2025-10-08 07:42:31 +03:00
George Hotz
e35152a004
work
2025-10-08 12:34:07 +08:00
George Hotz
d823a6d9d5
fast rangeify
2025-10-08 12:19:43 +08:00
qazal
84597ed53c
early assert for device mistmatched asts in rangeify ( #12499 )
...
* early assert for device mistmatched asts in rangeify
* alt also passes
2025-10-08 07:19:36 +03:00
qazal
2e19354c1c
viz: reorder timeline graphs ( #12498 )
...
* viz: reorder timeline graphs
* update test_viz with the new order
2025-10-08 07:10:23 +03:00
George Hotz
d06226b575
fix SPEC and all_tensors iterator ( #12496 )
2025-10-07 23:18:17 -04:00
qazal
a7cb80bfab
use recursive_property in UOp device ( #12477 )
...
* simple failing test with RecursionError
* switch to @recursive_property
* merge 2
* diff
2025-10-08 06:15:05 +03:00
George Hotz
d23324779c
rtoposort is fast, can replace rangeify with this
2025-10-08 11:06:12 +08:00
George Hotz
a6d59a0b45
backward_slice to get srcs recursively ( #12494 )
...
* change name to backward_slice
* faster check
* clean up comments and names
* comment
2025-10-08 10:31:42 +08:00
chenyu
eb3bc277b3
remove ASSERT_MIN_STEP_TIME in external_benchmark_openpilot ( #12495 )
...
should add for compile3 and compile 3 only
2025-10-07 22:13:42 -04:00
qazal
239f9a3029
update viz to not use children [pr] ( #12493 )
2025-10-08 04:35:01 +03:00
Sieds Lykles
b465c17b56
Revert "UOp.factor and add chain sorting ( #12413 )" ( #12492 )
...
This reverts commit e74be4a140
2025-10-08 03:20:23 +02:00
George Hotz
945cc46475
delete children tracking from uop ( #12491 )
...
* delete children tracking from uop
* uop children no longer exists
* no tracked children
* that test is flaky too
2025-10-08 09:04:14 +08:00
nimlgen
648e5bb223
hcq: do not raise when fini ( #12487 )
...
* hcq: do not raise when fini
* Revert "hcq: do not raise when fini"
This reverts commit 44af5f7d05
2025-10-07 23:27:03 +08:00
George Hotz
a2345787b9
parents is faster than sparents ( #12490 )
2025-10-07 21:31:50 +08:00
George Hotz
12c4963489
add more rangeify pm tests ( #12488 )
2025-10-07 05:45:38 -04:00
