Commit graph

9,739 commits

Author SHA1 Message Date
George Hotz
d3c8f09579 fix lil failure 2025-08-07 13:55:36 -07:00
George Hotz
3969d8574d
Merge branch 'master' into simpler_fusion 2025-08-07 13:46:42 -07:00
George Hotz
6ed2dfd187
delete the arange dim mismatch restriction (#11568)
* delete the arange dim mismatch restriction

* skip that test race
2025-08-07 13:46:17 -07:00
George Hotz
174747efb3 no copy 2025-08-07 13:13:50 -07:00
George Hotz
aaec715fa8 fuse_range + MSTACK fix 2025-08-07 13:03:53 -07:00
wozeparrot
7ae4335127
feat: generate blend index (#11566) 2025-08-07 14:20:28 -04:00
chenyu
594cbdc66f
skip AM ResNet50 benchmark (#11565)
hanging with FUSE_ARANGE?
2025-08-07 14:07:01 -04:00
George Hotz
de7b4b10af
Merge branch 'master' into simpler_fusion 2025-08-07 10:46:54 -07:00
chenyu
aa1a6f2132
support threshold in Tensor.softplus (#11564)
fix gradient for large input
2025-08-07 13:43:18 -04:00
George Hotz
807392be8b
Merge branch 'master' into simpler_fusion 2025-08-07 10:41:11 -07:00
chenyu
7ee3770961
FUSE_ARANGE=1 (#11427)
* FUSE_ARANGE=1

* fix test

---------

Co-authored-by: George Hotz <72895+geohot@users.noreply.github.com>
2025-08-07 13:32:34 -04:00
George Hotz
4dfcfb1ae5 Revert "Revert "viz: align-center checkbox (#11555)""
This reverts commit c52facfd29.
2025-08-07 08:15:57 -07:00
George Hotz
7e42427a7b Revert "Revert "viz: remove color for unbind step (#11554)""
This reverts commit 5650c7b86c.
2025-08-07 08:15:51 -07:00
George Hotz
dc765fbeb7 Revert "viz: timeline perf (#11533)"
This reverts commit 031f26632b.
2025-08-07 08:08:51 -07:00
George Hotz
5650c7b86c Revert "viz: remove color for unbind step (#11554)"
This reverts commit 1e205775bd.
2025-08-07 08:08:50 -07:00
George Hotz
c52facfd29 Revert "viz: align-center checkbox (#11555)"
This reverts commit 91ec093464.
2025-08-07 08:08:50 -07:00
George Hotz
974cfbe76d Revert "viz: add support for colored tooltip text (#11556)"
This reverts commit b3f7ea6f93.
2025-08-07 08:08:49 -07:00
George Hotz
3bf0db80ef Revert "viz: pick the largest rect for proxy fillColor (#11558)"
This reverts commit 76079bc7f2.
2025-08-07 08:08:48 -07:00
George Hotz
27c3c67e7c
Merge branch 'master' into simpler_fusion 2025-08-07 07:59:07 -07:00
George Hotz
9764c6cdee
fix mismatch reduce, try 2 (#11560)
* fix mismatch reduce, try 2

* fix heuristic

* delete that test

* don't start allowing ones
2025-08-07 07:57:58 -07:00
qazal
76079bc7f2
viz: pick the largest rect for proxy fillColor (#11558) 2025-08-07 16:40:17 +03:00
nimlgen
4f29a2c441
fix flaky test on macos (#11557) 2025-08-07 15:55:35 +03:00
qazal
b3f7ea6f93
viz: add support for colored tooltip text (#11556) 2025-08-07 15:04:43 +03:00
qazal
91ec093464
viz: align-center checkbox (#11555) 2025-08-07 14:22:02 +03:00
qazal
1e205775bd
viz: remove color for unbind step (#11554) 2025-08-07 14:16:21 +03:00
nimlgen
031f26632b
viz: timeline perf (#11533)
* viz: timeline perf

* progress

* fast

* less lines

* less lines

* less lines

* fix chrome
2025-08-07 13:16:17 +03:00
George Hotz
a1aa5670aa
Revert "fix mismatch reduce (#11547)" (#11549)
This reverts commit 49d21a9055.
2025-08-06 22:43:15 -07:00
George Hotz
0dbaa6293c
Merge branch 'master' into simpler_fusion 2025-08-06 22:42:53 -07:00
George Hotz
49d21a9055
fix mismatch reduce (#11547)
* fix mismatch reduce

* cleanups

* fix shape

* fix mypy

* resolve
2025-08-06 21:12:51 -07:00
George Hotz
625ecb9fec simpler fusion logic 2025-08-06 17:53:28 -07:00
George Hotz
21570545d3
move view pushing to codegen, try 2 (#11534)
* move view pushing to codegen, try 2

* fix up some linearizer tests

* fix test search

* fix test schedule

* delete that test

* fix test arange

* fix a few tests

* update tests

* push views

* ebs cleanup

* fix local/reg

* test and lint

* fix more tests

* test cleanups

* skipped that one
2025-08-06 15:58:38 -07:00
wozeparrot
2d5bdc939d
faster llama3 dataloader (#11540) 2025-08-06 18:25:57 -04:00
George Hotz
80d9cced07
more test cleanups (#11544)
* more test cleanups

* revert that
2025-08-06 15:05:21 -07:00
George Hotz
6fd1332763
update some tests for less Kernel (#11543)
* update some tests for less Kernel

* get_program update
2025-08-06 14:19:59 -07:00
George Hotz
09dc7af8e9
move bind to big graph (#11539)
* move bind to big graph

* fix tests

* unbind inside kernel only

* merge views

* fix multitensor

* failure text change
2025-08-06 13:27:51 -07:00
George Hotz
7c5e115747
test_mismatch_reduce (#11538) 2025-08-06 10:02:14 -07:00
George Hotz
4fe11725c6
pass through sink arg, update linearizer test (#11536)
* pass through sink arg, update linearizer test

* get_program help

* bump line count

* use new api
2025-08-06 09:48:48 -07:00
George Hotz
bfebb5c37b
do store in the replace_buffers (#11535) 2025-08-06 08:42:45 -07:00
geohotstan
1163292759
move onnx_parser into onnx (#11530) 2025-08-06 10:46:27 -04:00
George Hotz
7b16fadd87
load view late + simpler rewrite (#11525)
* add the load view later

* simpler replace buffers

* rewrite name
2025-08-06 06:55:11 -07:00
nimlgen
930d8dae0c
hcq: lazy prof signal allocation (#11531) 2025-08-06 15:28:11 +03:00
nimlgen
eafc7fda12
upd perfetto (#11528) 2025-08-06 14:00:34 +03:00
nimlgen
1afb290027
ci: fix runner in nv (#11527) 2025-08-06 10:38:04 +03:00
qazal
61dae0685c
viz: show total mem in tooltip (#11526) 2025-08-06 06:51:26 +03:00
George Hotz
cf66df0ea6
put load early to make pointers match (#11524) 2025-08-05 20:04:32 -07:00
George Hotz
92175626e3
prereqs: move views to codegen (#11522) 2025-08-05 19:27:58 -07:00
chenyu
c9225d22ce
only disable flaky test_jit_multidev_xfer (#11523) 2025-08-05 22:17:25 -04:00
George Hotz
f58fd3143d
cleanup fix_kernel (#11520)
* cleanup fix_kernel

* early load buffer

* early meta ops

* move those to fix_kernel_ops

* fix tests

* remote metal was flaky

* Revert "fix tests"

This reverts commit a27019383d.

* that hack broke things

* fine for ptx
2025-08-05 18:38:43 -07:00
George Hotz
067daee5be
pin torch to 2.7.1 (#11519) 2025-08-05 15:58:57 -07:00
George Hotz
b39f43c46a
optimize in rewrite, try 2 (#11518)
* changes

* fix test uops

* optimize in rewrite, try 2
2025-08-05 15:52:53 -07:00