George Hotz and GitHub
eb3f2d8564
Merge branch 'master' into prealloc_bufs
2026-02-19 14:24:22 +08:00
George Hotz and GitHub
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
7143de0268
fix custom kernel
2026-02-19 12:47:33 +08:00
geohot
e50e5e626e
skips
2026-02-19 12:42:41 +08:00
geohot
619362530e
29 failures
2026-02-19 12:36:09 +08:00
geohot
db2f41c92d
no shrink in the graph
2026-02-19 12:31:20 +08:00
geohot
4850178108
dedup
2026-02-19 12:21:00 +08:00
geohot
74e767d5ac
same 37 failures
2026-02-19 12:18:51 +08:00
qazal and GitHub
5bc65ec669
applied_opts/estimates in program spec are aliases for the sink arg ( #14860 )
...
* remove applied_opts from programspec
* comment that out
* placement
* update tests
* p.ast.arg
* remove todo comment
* maybe this too
* it can exist as an alias, also for estimates
2026-02-19 13:08:26 +09:00
chenyu and GitHub
8d8da185ec
minor handle_allreduce cleanup [pr] ( #14876 )
...
no more lbs, also use a divmod
2026-02-18 22:53:28 -05:00
sirhcm and GitHub
b5588d341b
uop_given_valid fixes many gated reads for IMAGE=1 ( #14877 )
...
* add replay script
* pkl is arg
* that needs uop_given_valid
* cleanup
2026-02-18 22:49:47 -05:00
George Hotz and GitHub
ec14daf0b7
Merge branch 'master' into prealloc_bufs
2026-02-19 11:37:53 +08:00
George Hotz and GitHub
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
chenyu and GitHub
0c85b93938
support shink sharded and non-sharded axes ( #14874 )
...
simpler to just support it
2026-02-18 20:54:10 -05:00
George Hotz and GitHub
7d40b84390
Merge branch 'master' into prealloc_bufs
2026-02-19 09:46:03 +08:00
chenyu and GitHub
e8252e6e4f
use offical gguf in test ( #14872 )
...
also deleted bad test_load_sample_mxfp4, added some hard coded simple tests
2026-02-18 19:55:09 -05:00
chenyu and GitHub
8c830c5b44
test_full_like_shrink_on_shard_axis ( #14870 )
...
* test_full_like_shrink_on_shard_axis
add a test case that triggers non-copy branch in mstack_early_shrink
* 0
2026-02-18 19:23:44 -05:00
Ananta Ranganathan and GitHub
4005e9db6d
Mxfp4 fix ( #14866 )
...
* double e2m1 values for mxfp4
* check if assert equal works in ci
* Revert "check if assert equal works in ci"
This reverts commit 8cf902ce0d .
* remove unnecessary whitespace change
* add test case that fails for old implementation but passes for new
* add note that the previous test is bad
* clarification on the methodology for the test
* fix the indent problem that happened to skip this test
* for now update mxfp4 block test to similarly use allclose (bad)
* add gist link and clearer explanation of process for computing test data
2026-02-18 18:50:59 -05:00
chenyu and GitHub
0e4cf21a75
remove handle_allreduce_multirank and group_id [pr] ( #14869 )
...
leftovers from ops_remote
2026-02-18 16:13:54 -05:00
chenyu and GitHub
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
chenyu and GitHub
f84a11bb9f
delete uneven shard tests and mentions ( #14867 )
2026-02-18 14:10:33 -05:00
nimlgen and GitHub
1c8c17a593
am: aca ( #14861 )
2026-02-18 21:40:09 +03:00
chenyu and GitHub
b3cdb61067
clean up expand_multi [pr] ( #14865 )
...
remove dead assert, also make it more like a view
2026-02-18 12:21:13 -05:00
chenyu and GitHub
0260406f49
simplify reshape_multi [pr] ( #14864 )
2026-02-18 11:46:26 -05:00
chenyu and GitHub
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
nimlgen and GitHub
3b95fa0ed4
am_smi: enable mem usage back ( #14858 )
2026-02-18 19:27:27 +03:00
geohot
262984167c
tests skips
2026-02-18 19:43:51 +08:00
George Hotz and GitHub
31421a7be4
Merge branch 'master' into prealloc_bufs
2026-02-18 19:33:44 +08:00
geohot
6c45c1b0fb
mypy fixes
2026-02-18 19:32:59 +08:00
geohot
b2f025b359
shrink axis correction
2026-02-18 19:31:21 +08:00
qazal and GitHub
a212881130
viz: second profiler link goes to source code ( #14855 )
2026-02-18 19:40:34 +09:00
geohot
628157c944
fix tests
2026-02-18 18:29:27 +08:00
geohot
0fd7db8a9a
type and buffer
2026-02-18 18:19:25 +08:00
geohot
9c06898222
mnist should be contiguious
2026-02-18 18:10:02 +08:00
qazal and GitHub
b0110c4469
viz: simplify shape clicking ( #14853 )
...
* setFocus is the more clear name
* do less
2026-02-18 19:03:26 +09:00
geohot
5446772cdd
fix schedule tests
2026-02-18 18:00:41 +08:00
George Hotz and GitHub
0cc6c2d26d
Merge branch 'master' into prealloc_bufs
2026-02-18 17:44:26 +08:00
George Hotz and GitHub
af839b2bd1
remove all the outerworld stuff, it was too complex ( #14852 )
2026-02-18 17:44:11 +08:00
geohot
ed202ac5a3
don't check that anymore
2026-02-18 16:55:03 +08:00
geohot
44c139a5b6
bugfixes
2026-02-18 16:42:27 +08:00
geohot
b661b5a130
162 failures
2026-02-18 16:35:22 +08:00
geohot
bc118562b6
fix multi
2026-02-18 16:32:01 +08:00
geohot
2bb1cd3ae4
fix symbolic stuff
2026-02-18 16:02:14 +08:00
geohot
8cfb787453
fixes disk tensor stuff
2026-02-18 15:12:39 +08:00
geohot
2282d42ecb
disk bufs
2026-02-18 15:04:26 +08:00
wozeparrot and GitHub
6d301ad2c4
feat: llama wqkv ( #14841 )
2026-02-17 23:01:33 -08:00
qazal and GitHub
a3d516c4b5
viz: start displaying pma ( #14848 )
...
* viz: start displaying pma
* s
* work
* colors
* cleaner
* max packets
* fine
* work
* pma
* diff cleanup
2026-02-18 14:22:32 +09:00
George Hotz and GitHub
4db1336ddd
Merge branch 'master' into prealloc_bufs
2026-02-18 12:24:16 +08:00