Commit Graph
11453 Commits
Author SHA1 Message Date
Sieds LyklesandGitHub 10540414cd Add Ops.CMPEQ (#10431)
* Add op

* add to Groupop.ALU

* fix spec

* fix ptx

* temporary pickle by name to see process replay

* add Ops.EQ to binary ops

* Actuall rename properly

* add test to assert CMPEQ is being used

* Ops.CMPEQ is automatic cast to bool

* add Ops.CMPEQ to llvm

* add Ops.CMPEQ to llvm
2025-08-10 13:13:16 +02:00
chenyuandGitHub f7aa1b85fe minor sort cleanups (#11602) 2025-08-10 01:51:23 -04:00
chenyuandGitHub dfb702ef33 fix sort for small dim (#11601)
* fix sort for small dim

* fixed test_sort_empty
2025-08-10 01:17:41 -04:00
chenyuandGitHub ef17af85c6 remove .float call in llama logit (#11598)
* remove .float call in llama logit

* bfloat item
2025-08-10 00:02:18 -04:00
chenyuandGitHub dd3d2eb36c add training llama3 test in ci (#11599) 2025-08-09 22:35:39 -04:00
chenyuandGitHub 3e64467322 remove freqs_cis contiguous in llama (#11597) 2025-08-09 21:11:12 -04:00
chenyuandGitHub 7338ffead0 small beautiful_mnist update (#11596)
gather is fast now. there's a conv/bw kernel that only gets fast with BEAM, but whole thing runs < 5 seconds now regardless
2025-08-09 19:51:14 -04:00
chenyuandGitHub 45baec1aab model parallel llama (#11588)
MP=8 GRADIENT_ACC_STEPS=3 BS=1 DEFAULT_FLOAT=bfloat16 OPTIM_DTYPE=bfloat16 LLAMA3_SIZE=70B SEQLEN=512 PYTHONPATH=. MODEL=llama3 python3 examples/mlperf/model_train.py
2025-08-09 16:54:27 -04:00
nimlgenandGitHub 09bc377da3 search: print runtime failures on debug (#11593) 2025-08-09 23:01:19 +03:00
nimlgenandGitHub 14f99ff1a1 amd: doorbell_cpu_addr is not used (#11592)
* amd: doorbell_cpu_addr is not used

* hm
2025-08-09 20:03:21 +03:00
Sieds LyklesandGitHub 01c770c77b Fix z3 float cast in indexing (#11590)
* adjust dtype of z3_renderer and add rule for cast

* dtypes.bool is also cast noop

* add regression test

* make embedding smaller

* even smaller test
2025-08-09 17:59:23 +02:00
Sieds LyklesandGitHub 10d388499d Refactor optional.py (#11578)
* move fast_idiv to transcendental

* move optional.py

* adjust comment

* change import

* mypy needs this?
2025-08-09 17:35:05 +02:00
nimlgenandGitHub 20e46a175c do not use disk with usb (#11119)
* not use disk with usb

* better name
2025-08-09 11:58:02 +03:00
qazalandGitHub 53179953fc viz: factor out memory graph render (#11586) 2025-08-08 20:18:11 +03:00
qazalandGitHub 8ce72d3fad simpler disassembly table spec (#11583)
* simpler disassembly table spec

* update ui

* move to scalar/vec render
2025-08-08 17:59:26 +03:00
qazalandGitHub 44a222a9b2 viz: move resource usage summary to server (#11582) 2025-08-08 17:08:28 +03:00
qazalandGitHub 793ace530e update amd_uop_matmul.py import (#11581)
Using this for testing SQTT
2025-08-08 17:07:35 +03:00
chenyuandGitHub b232c60def benchmark openpilot 0.9.9 (#11575)
* benchmark openpilot 0.9.9

not sure what to do with the 0.9.7 ones with IMAGE=2 and validate

* name
2025-08-08 01:26:14 -04:00
qazalandGitHub 16f0edbe90 pass opts arg in get_program process replay [pr] (#11571)
* fix ptx process replay

* keyword arg

* renderer is also optional [pr]

* test_linearizer fixup

* name function order is args,ret,kwargs

* can use opts_to_apply

* pass through p.applied_opts

* sink_arg

* now it opens devices too
2025-08-08 03:05:09 +03:00
qazalandGitHub 960cc6533a pass through name function args in track_rewrites (#11572) 2025-08-08 02:28:52 +03:00
wozeparrotandGitHub 1826004ef9 feat: add tinyos builder link (#11570) 2025-08-07 17:42:18 -04:00
George HotzandGitHub 82be8abfd2 move opt under codegen (#11569) 2025-08-07 14:19:17 -07:00
chenyuandGitHub 702e38dc19 remove FUSE_ARANGE_UINT (#11567)
also add IGNORE_OOB=1 to bert runs. lowered BS on tinybox to 90 since 96 oom during eval without reset
2025-08-07 16:49:06 -04:00
George HotzandGitHub 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
wozeparrotandGitHub 7ae4335127 feat: generate blend index (#11566) 2025-08-07 14:20:28 -04:00
chenyuandGitHub 594cbdc66f skip AM ResNet50 benchmark (#11565)
hanging with FUSE_ARANGE?
2025-08-07 14:07:01 -04:00
chenyuandGitHub aa1a6f2132 support threshold in Tensor.softplus (#11564)
fix gradient for large input
2025-08-07 13:43:18 -04:00
7ee3770961 FUSE_ARANGE=1 (#11427)
* FUSE_ARANGE=1

* fix test

---------

Co-authored-by: George Hotz <[email protected]>
2025-08-07 13:32:34 -04:00
geohot 4dfcfb1ae5 Revert "Revert "viz: align-center checkbox (#11555)""
This reverts commit c52facfd29.
2025-08-07 08:15:57 -07:00
geohot 7e42427a7b Revert "Revert "viz: remove color for unbind step (#11554)""
This reverts commit 5650c7b86c.
2025-08-07 08:15:51 -07:00
geohot dc765fbeb7 Revert "viz: timeline perf (#11533)"
This reverts commit 031f26632b.
2025-08-07 08:08:51 -07:00
geohot 5650c7b86c Revert "viz: remove color for unbind step (#11554)"
This reverts commit 1e205775bd.
2025-08-07 08:08:50 -07:00
geohot c52facfd29 Revert "viz: align-center checkbox (#11555)"
This reverts commit 91ec093464.
2025-08-07 08:08:50 -07:00
geohot 974cfbe76d Revert "viz: add support for colored tooltip text (#11556)"
This reverts commit b3f7ea6f93.
2025-08-07 08:08:49 -07:00
geohot 3bf0db80ef Revert "viz: pick the largest rect for proxy fillColor (#11558)"
This reverts commit 76079bc7f2.
2025-08-07 08:08:48 -07:00
George HotzandGitHub 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
qazalandGitHub 76079bc7f2 viz: pick the largest rect for proxy fillColor (#11558) 2025-08-07 16:40:17 +03:00
nimlgenandGitHub 4f29a2c441 fix flaky test on macos (#11557) 2025-08-07 15:55:35 +03:00
qazalandGitHub b3f7ea6f93 viz: add support for colored tooltip text (#11556) 2025-08-07 15:04:43 +03:00
qazalandGitHub 91ec093464 viz: align-center checkbox (#11555) 2025-08-07 14:22:02 +03:00
qazalandGitHub 1e205775bd viz: remove color for unbind step (#11554) 2025-08-07 14:16:21 +03:00
nimlgenandGitHub 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 HotzandGitHub a1aa5670aa Revert "fix mismatch reduce (#11547)" (#11549)
This reverts commit 49d21a9055.
2025-08-06 22:43:15 -07:00
George HotzandGitHub 49d21a9055 fix mismatch reduce (#11547)
* fix mismatch reduce

* cleanups

* fix shape

* fix mypy

* resolve
2025-08-06 21:12:51 -07:00
George HotzandGitHub 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
wozeparrotandGitHub 2d5bdc939d faster llama3 dataloader (#11540) 2025-08-06 18:25:57 -04:00
George HotzandGitHub 80d9cced07 more test cleanups (#11544)
* more test cleanups

* revert that
2025-08-06 15:05:21 -07:00
George HotzandGitHub 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 HotzandGitHub 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 HotzandGitHub 7c5e115747 test_mismatch_reduce (#11538) 2025-08-06 10:02:14 -07:00