geohot
f4e1b93225
fix beam
2025-08-29 19:05:49 -07:00
geohot
4a31c319b3
work
2025-08-29 18:42:50 -07:00
geohot
59081645f7
beam in RKernel
2025-08-29 18:42:50 -07:00
George Hotz and GitHub
6e57905c6d
Merge branch 'master' into working_postopt
2025-08-29 12:37:01 -07:00
b2cc06218a
python bfloat16 ( #11912 )
...
* python bf16
* _to_torch_storage_type
---------
Co-authored-by: b1tg <[email protected]
2025-08-29 15:18:02 -04:00
George Hotz and GitHub
40606c60b0
Merge branch 'master' into working_postopt
2025-08-29 11:23:17 -07:00
George Hotz and GitHub
afad7d0cd1
remove dtype from range, it will be dtypes.index soon [pr] ( #11914 )
...
* remove dtype from range, it will be dtypes.index soon [pr]
* a few more
2025-08-29 09:52:07 -07:00
George Hotz and GitHub
80986321eb
Merge branch 'master' into working_postopt
2025-08-29 09:43:05 -07:00
qazal and GitHub
30e72d5820
multi device and copy tracing for NULL device ( #11913 )
...
* add device name to NULL programs
* trace transfers
2025-08-29 15:31:00 +03:00
qazal and GitHub
d8e1e4dc61
tracing: show NULL programs ( #11911 )
2025-08-29 14:09:33 +03:00
nimlgen and GitHub
75678b2cbe
amd: retire pm4 xcc sync ( #11835 )
...
* amd: aql default when several xccs
* amd: retire om4 xcc sync
* remove more
* more
* more
2025-08-29 09:56:27 +03:00
George Hotz and GitHub
bd263cbcb0
Merge branch 'master' into working_postopt
2025-08-28 15:13:02 -07:00
George Hotz and GitHub
394c2d1db1
update Kernel API in tests + move optimize_local_size ( #11907 )
2025-08-28 15:12:47 -07:00
geohot
2e41472b02
support tc 2, all are pad
2025-08-28 14:40:50 -07:00
geohot
ac641f7b10
support tc padding
2025-08-28 14:34:42 -07:00
geohot
226c59fa5a
bugfix
2025-08-28 14:13:34 -07:00
geohot
3bbfcbccde
work
2025-08-28 13:55:07 -07:00
nimlgen and GitHub
fa695ac1ce
ci: mac gpuocelot ( #11906 )
...
* gm
* fix?
* ops
* imp
* xx
* add file
2025-08-28 23:29:43 +03:00
geohot
78a56b3461
fix some tests
2025-08-28 12:55:12 -07:00
George Hotz and GitHub
b5ac4501d4
Merge branch 'master' into working_postopt
2025-08-28 12:35:39 -07:00
George Hotz and GitHub
b9b438c516
small updates from postopt ( #11903 )
...
* tests from postopt
* modernize
* skip lin tests
* that's fixed?
* skip, not failure
2025-08-28 12:34:52 -07:00
nimlgen and GitHub
bb55a3001f
nv: flush reset message ( #11897 )
2025-08-28 22:17:20 +03:00
geohot
038d3bc295
clean up test
2025-08-28 11:39:02 -07:00
geohot
4b223c820a
fix test
2025-08-28 11:29:02 -07:00
nimlgen and GitHub
e8289c75b1
ci: do not reinstall existing pkgs in macos ( #11900 )
2025-08-28 21:20:15 +03:00
geohot
528e285d81
more tests
2025-08-28 11:15:47 -07:00
geohot
cd3dc67636
tensor cores need to pad
2025-08-28 11:04:30 -07:00
geohot
b19a8963c3
revert
2025-08-28 11:00:20 -07:00
George Hotz and GitHub
ec10e00cf5
Merge branch 'master' into working_postopt
2025-08-28 10:50:00 -07:00
geohot
d3aa38ad4a
work
2025-08-28 10:46:18 -07:00
chenyu and GitHub
134cf56904
update cache name for gpuocelot ( #11896 )
2025-08-28 13:11:10 -04:00
ea1be2e4cd
[bounty] Remove using reshape to register symbolic shape ( #11771 )
...
* Modify tests and start work towards removing symbolic reshape
* Refactor symbolic reshape
* fix small error
* much cleaner + fix more tests
* Can remove this now
* Update test_symbolic_ops and test_tiny
* Couple more tests
* Unused import
* More tests and add EXPAND to Tensor.empty
* Fix test beam search
* all int
* Fix rangeify by adding shrink
* Remove OOB check and so fix test_symbolic_jit
* test_symbolic_jit doesn't need OOB Context anymore either
* Should remove that test now
* Cleanups part 1
* fix linters
* Final cleanups
* Don't reassign inside for loop
---------
Co-authored-by: chenyu <[email protected]
2025-08-28 12:30:49 -04:00
qazal and GitHub
53853ae49b
viz: switch to Path2D ( #11892 )
2025-08-28 18:58:16 +03:00
nimlgen and GitHub
874c1db4af
am: init support for aql ( #11888 )
2025-08-28 18:41:46 +03:00
17ecaf4682
Add test_variable_empty ( #11889 )
...
* Add test_variable_empty
* Move test and add TODO
---------
Co-authored-by: chenyu <[email protected]
2025-08-28 11:38:27 -04:00
Nino Risteski and GitHub
54be477152
rope cache optim for jit prune in llm.py ( #11678 )
...
* rope cache optim for jit prune
* rope test
* tests in test attention
* Revert "rope test"
This reverts commit 69ede543d0
2025-08-28 08:31:29 -07:00
geohot
6e41040e91
get tc ranges
2025-08-28 08:24:33 -07:00
geohot
6b3d9d6663
fix some tests
2025-08-28 08:07:45 -07:00
geohot
0ece218588
fix uop test
2025-08-28 07:34:06 -07:00
quortus and GitHub
5f8fe9a331
Replace ASSIGN with STORE in test_linearizer ( #11821 )
2025-08-28 07:33:20 -07:00
geohot
feb12685f2
postopt using RKernel
2025-08-28 07:28:52 -07:00
4e8370309c
Support onnx If OP ( #11648 )
...
* start
* tiny clean up
* whoops, didn't mean to accidentally fix this
* fix .to(device), kinda hacky and this fix makes it slower?
* merge properly
* FINALLY figured out slowness, also hack pylint for now
* add DEBUGONNX print for subgraph
* oops
* WOOOOOOOO SHAPE CACHE 50% SPEED INCREASE
* small fix, but maybe all deterministic Tensor creation in fp should be cached
* cache condition
* sliiiightly cleaner
* better abstraction?
* remove sam from model_benchmark
* remove shape cache speed up for now
* less lines
* isinstance fix
---------
Co-authored-by: chenyu <[email protected]
2025-08-28 10:17:35 -04:00
George Hotz and GitHub
6d6f0dada7
support for tuple ranges ( #11890 )
...
* support for tuple ranges
* breaks it
2025-08-28 07:02:31 -07:00
nimlgen and GitHub
60dd9a162c
memory: tiny tlsf cleanup ( #11887 )
2025-08-28 14:07:18 +03:00
chenyu and GitHub
beb5982165
FUSE_ATTENTION ( #11884 )
2025-08-27 19:59:17 -04:00
George Hotz and GitHub
cb5295168d
postrange boilerplate work ( #11881 )
2025-08-27 15:22:59 -07:00
George Hotz and GitHub
fd579433bc
pre expander shouldn't go in gpudims ( #11880 )
2025-08-27 14:52:24 -07:00
nimlgen and GitHub
44816218b5
memplan: fix large buffers planning ( #11878 )
...
* memplan: fix large buffers planning
* fix
* fix dsp
2025-08-27 23:54:27 +03:00
nimlgen and GitHub
4006366752
Revert "memplan: fix large buffers planning ( #11876 )" ( #11877 )
...
This reverts commit 7f90497efc
2025-08-27 22:36:14 +03:00
nimlgen and GitHub
7f90497efc
memplan: fix large buffers planning ( #11876 )
...
* memplan: fix large buffers planning
* fix
2025-08-27 22:04:15 +03:00
geohot
