chenyu
8d8da185ec
minor handle_allreduce cleanup [pr] ( #14876 )
...
no more lbs, also use a divmod
2026-02-18 22:53:28 -05:00
Christopher Milan
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
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
0c85b93938
support shink sharded and non-sharded axes ( #14874 )
...
simpler to just support it
2026-02-18 20:54:10 -05:00
chenyu
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
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
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
2026-02-18 18:50:59 -05:00
chenyu
0e4cf21a75
remove handle_allreduce_multirank and group_id [pr] ( #14869 )
...
leftovers from ops_remote
2026-02-18 16:13:54 -05:00
chenyu
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
f84a11bb9f
delete uneven shard tests and mentions ( #14867 )
2026-02-18 14:10:33 -05:00
nimlgen
1c8c17a593
am: aca ( #14861 )
2026-02-18 21:40:09 +03:00
chenyu
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
0260406f49
simplify reshape_multi [pr] ( #14864 )
2026-02-18 11:46:26 -05:00
chenyu
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
3b95fa0ed4
am_smi: enable mem usage back ( #14858 )
2026-02-18 19:27:27 +03:00
qazal
a212881130
viz: second profiler link goes to source code ( #14855 )
2026-02-18 19:40:34 +09:00
qazal
b0110c4469
viz: simplify shape clicking ( #14853 )
...
* setFocus is the more clear name
* do less
2026-02-18 19:03:26 +09:00
George Hotz
af839b2bd1
remove all the outerworld stuff, it was too complex ( #14852 )
2026-02-18 17:44:11 +08:00
wozeparrot
6d301ad2c4
feat: llama wqkv ( #14841 )
2026-02-17 23:01:33 -08:00
qazal
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
d5636fba90
assign after copy shouldn't contig ( #14847 )
...
* assign after copy shouldn't contig
* fix assign copy
2026-02-18 12:23:49 +08:00
George Hotz
ab55e8c6b9
assign should be used as output buffer ( #14845 )
...
* assign should be used as buffer
* late removed
* the fix
* better fix
* backward slice
2026-02-18 09:37:46 +08:00
chenyu
e3c120c8e1
exclude 100 in test_assign_add ( #14846 )
...
this can crash, not sure why. skip 100 to see if it's better
2026-02-17 19:12:47 -05:00
Christopher Milan
7641ed61af
remove doublecast in IMAGE=1 ( #14839 )
2026-02-17 18:22:14 -05:00
Christopher Milan
5b11519d5e
LLVM actually supports ops ( #14843 )
...
LLVM should support eg, SHL/SHR, but this was never actually rendered
2026-02-17 18:21:33 -05:00
wozeparrot
95e97ec341
seperate llama optim ( #14810 )
2026-02-17 13:02:35 -08:00
chenyu
72cf603805
removed if self.buffer.is_allocated() in realized ( #14836 )
...
automatically fixes is_realized issue for empty
2026-02-17 15:35:56 -05:00
chenyu
aec8a6c85b
Revert "one run_schedule for assign realize ( #14835 )" ( #14837 )
...
This reverts commit df7c37f611
2026-02-17 14:34:26 -05:00
chenyu
df7c37f611
one run_schedule for assign realize ( #14835 )
...
concat schedules. separate out the execution part
2026-02-17 14:01:55 -05:00
chenyu
61867c2f35
TestRealizeIsRealized ( #14834 )
...
test after calling .realize(), uop.is_realized is True. currently not working for empty (thus disk tensor), and const
2026-02-17 13:30:35 -05:00
chenyu
f147791105
update test to reset and test kernel_count directly ( #14832 )
2026-02-17 11:48:46 -05:00
chenyu
9d4937ab5e
remove assign test @unittest.skip("this test is crashing!") ( #14831 )
2026-02-17 10:30:58 -05:00
nimlgen
dda5ccf63b
hcq: fix usb<->cpu mappings ( #14827 )
...
* hcq: fix usb<->cpu mappings
* non cpu
* um
2026-02-17 18:04:18 +03:00
nimlgen
801677cf12
am: GCVM_L2_PROTECTION_FAULT_STATUS prints device ( #14830 )
2026-02-17 18:03:52 +03:00
chenyu
f07898c68a
move assign chain fix to rangeify ( #14829 )
2026-02-17 09:40:34 -05:00
nimlgen
a2586e4c70
nv: move reset earlier ( #14824 )
2026-02-17 17:25:49 +03:00
chenyu
f2f039cc0f
fix chained full-buffer assign ( #14828 )
...
this shows issue that pm_remove_bufferize drops tags, will fix in bufferize next. this also fixed rand being different in jit vs no-jit
2026-02-17 09:11:04 -05:00
chenyu
58fa82eef5
stronger test_assign_add ( #14826 )
...
also test self add 10 and 100 times
2026-02-17 08:36:09 -05:00
George Hotz
ff60dab622
Revert "big sink is on base ( #14819 )" ( #14825 )
...
This reverts commit 5fc3d8109f
2026-02-17 19:18:06 +08:00
qazal
f8e485ee9e
nvcc/nvdisasm macos shim ( #14822 )
...
* move to backend
* and arch
* setup_nvcc_osx
* blackwell
* min test
* now getting dumb assert is_ptx
* support cubin.
* work
* remove that
* simpler
2026-02-17 20:07:05 +09:00
qazal
d24781f45f
viz: do not, ever, open devices ( #14820 )
...
* viz: do not, ever, open devices
* unwrap
* on the kernel info
2026-02-17 19:42:44 +09:00
George Hotz
5fc3d8109f
big sink is on base ( #14819 )
...
* big sink is on base
* contiguous fixes tests
2026-02-17 18:32:56 +08:00
qazal
99a988b9d2
viz: remove ProgramSpec from trace ( #14818 )
2026-02-17 19:04:58 +09:00
qazal
f590564bf7
gemm multiple is only for cdna4 asm ( #14814 )
...
* gemm multiple is only for cdna4 asm
* move to backend
* and arch
* path
2026-02-17 14:00:02 +09:00
George Hotz
5bd2862d1a
late compile the cdna gemm ( #14783 )
...
* late compile the cdna gemm
* remove old things
* finalize inplace
---------
Co-authored-by: qazal <qazal.software@gmail.com >
2026-02-17 13:04:22 +09:00
Christopher Milan
275319c789
IMAGE=1 2d indexing ( #14809 )
...
* IMAGE=1 2d indexing
* cleanup
* oops
* go back to 'idx'
* fix vals
* fix
* ugh
2026-02-16 22:51:18 -05:00
George Hotz
f081f154ae
parameterize the CDNA asm gemm ( #14813 )
...
* parameterize the CDNA asm gemm
* fix llama test
* fix
* add more gemmt ests
* confirm all match
* test these asm gemms
2026-02-17 11:35:18 +08:00
George Hotz
bc3487d607
VIZ display cleanups ( #14811 )
...
* exclude reshape/expand broadcasts from viz
* limit src lines
2026-02-17 10:03:08 +08:00
chenyu
5bca5be2d2
test slice assign twice retains the buffer ( #14807 )
2026-02-16 20:01:47 -05:00
ridoy majumdar
ba39a19114
viz: remove duplicate Ops.PARAM color ( #14808 )
2026-02-17 09:31:47 +09:00
