qazal and GitHub
7a9f3dea54
assert a schedule double realize ( #7178 )
...
* assert this
* maybe use lazycache
* Revert "maybe use lazycache"
This reverts commit 7368102906 .
* set enable_cache=True
* assert 1 schedule
2024-10-21 14:16:21 +03:00
George Hotz and GitHub
be1806df47
fast sym infer [pr] ( #7177 )
...
* fast sym infer [pr]
* fix pylint
2024-10-21 17:31:32 +08:00
b6d9b276bb
GGUF support ( #7046 )
...
* basic loader, untested
* testing
* remove utils import in test
* q8_0
* q4_1
* end to end testing
* minor cleanup
* fix casting
* moved to state
* move tests
* move dequant to fn
* fix lint elif
* remove gguf from extra
* fix dict union
* q6_k simpler
* naming and spacing
* gpt2-gguf example
* cleanup
* move gguf example
* minor cleanup
---------
Co-authored-by: George Hotz <[email protected] >
2024-10-21 16:15:34 +08:00
qazal and GitHub
8074c0ec8f
skip test_bfloat16_unary on AMD ( #7169 )
2024-10-21 01:00:47 +03:00
qazal and GitHub
713461129b
scheduler ast rewrite reorders from big graph [pr] ( #7168 )
...
* scheduler ast rewrite reorders from big graph [pr]
* update test_uops.py
2024-10-21 00:47:58 +03:00
qazal and GitHub
1383df95af
track_rewrites by function call [pr] ( #7165 )
...
* named track_rewrites [pr]
* group all of create_schedule_with_vars
2024-10-20 17:45:25 +03:00
chenyu and GitHub
98de58260b
simplify valid itself ( #7112 )
2024-10-19 19:39:25 -04:00
chenyu and GitHub
f511ad9103
No pyint again ( #7156 )
...
* Revert "bring back pyint (#7150 )"
This reverts commit 37e83ca6fc .
* remove truncate in const folding
* truncate_output=False
2024-10-19 13:48:59 -04:00
nimlgen and GitHub
54c6a317f8
test_failure_54 ( #7155 )
...
* test_failure_54
* metal
2024-10-18 23:31:18 +03:00
chenyu and GitHub
37e83ca6fc
bring back pyint ( #7150 )
...
fixed test_failure_52 and resnet. need to understand this better
2024-10-18 14:54:37 -04:00
b0a13896d7
PtrDType is dataclass [pr] ( #7125 )
...
* PtrDType is dataclass [pr]
* new dataset
---------
Co-authored-by: chenyu <[email protected] >
2024-10-18 09:40:33 -04:00
chenyu and GitHub
ea016b55d1
don't throw in fuzz_linearizer ( #7148 )
...
already broken on master and needs fix. don't throw to not block other pr
2024-10-18 09:28:30 -04:00
Bhavya Gada and GitHub
b7b2017cb9
only ignore warnings not errors ( #7146 )
2024-10-18 07:41:11 -04:00
ignaciosica and GitHub
8bcdd7c97d
Refactor AMD pm rules to remove handwritten bf16 bool alus ( #7136 )
...
* refactor pm rules
- remove unused handwritten methods
- refactor amd pm rules to fix bug with bool alu
* add bf16 bool alu tests
* add bf16 tests
* hotfix: make atol consistent
2024-10-18 09:00:46 +08:00
Bhavya Gada and GitHub
534597e753
fix all test warnings ( #7024 )
...
* fix pytorch warning in nn.conv2d for same padding
* fix future warning in torch load
* fix overflow warning in tensor list test: https://github.com/numpy/numpy/issues/23606#issuecomment-1512752172
* fix floating point warnings in dtype tests using docs https://numpy.org/doc/stable/reference/generated/numpy.errstate.html and a neat solution https://stackoverflow.com/questions/53634965/change-np-seterr-behavior-inside-a-function-only
* put err state in one place; comment taken care of by function hover
* enter np errstate context manager on test setup
* put decorator on class
2024-10-18 08:56:40 +08:00
chenyu and GitHub
0cd4b93441
remove CStyleLanguage from test_uop_symbolic ( #7142 )
2024-10-17 19:39:34 -04:00
chenyu and GitHub
72ed66205d
enable test_resnet_half ( #7141 )
...
already worked so just fixed the test
2024-10-17 19:02:20 -04:00
chenyu and GitHub
12ff52b88b
test_failure_52 fails on real METAL ( #7138 )
2024-10-17 15:37:28 -04:00
chenyu and GitHub
84e98900e8
test linearizer failure 53 ( #7137 )
...
variable scope issue caused compile error
2024-10-17 15:23:43 -04:00
nimlgen and GitHub
45db7d9045
fuzz qcom vs opencl ( #7130 )
...
* fuzz qcom vs opencl
* fix nv
* bettre?
* typo
* open both devs
2024-10-17 18:49:08 +03:00
chenyu and GitHub
287a198c4f
increase test_strongly_connected_DAG threshold ( #7131 )
...
flaky
2024-10-17 11:08:50 -04:00
George Hotz and GitHub
ded1b38b84
minor dtype cleanup [pr] ( #7124 )
...
* minor dtype cleanup [pr]
* use ptr() function
2024-10-17 17:41:23 +08:00
George Hotz and GitHub
d990a16326
fix tests to use render ( #7116 )
2024-10-17 14:35:22 +08:00
chenyu and GitHub
842fe444df
test case for valid only simplification ( #7108 )
2024-10-16 16:40:46 -04:00
90eff347e2
tinytqdm write support ( #6359 )
...
* add write support
* add test
* update test case to compare write outputs
* assert final write output
* flush when using write
* update write logic
* Revert "update write logic"
This reverts commit 5e0e611b46 .
---------
Co-authored-by: chenyu <[email protected] >
2024-10-16 14:51:41 -04:00
nimlgen and GitHub
39ab67e9ef
beam capture and replay in fuzz ( #7099 )
...
* beam capture and reply in fuzz
* clean a bit
2024-10-16 20:26:58 +03:00
qazal and GitHub
9d5342976e
skip TestSetitem.test_setitem_inplace_operator ( #7103 )
2024-10-16 18:59:08 +03:00
qazal and GitHub
6acda43a2c
test a rewrite of permuted reduce [pr] ( #7093 )
...
* test a rewrite of permuted reduce [pr]
* addd rewrite tracker
* expected
* passes
2024-10-16 12:49:54 +03:00
qazal and GitHub
40f33c110b
big graph var_vals as rewrite context ( #7007 )
...
* var_vals as rewrite context
* no default arg
* add st var_vals
* delete some stuff
* add the rewrite rule again
* extra
* this whole part is preschedule
* test with a second context
* redo
* i always forget tensor variable
2024-10-16 07:31:44 +03:00
qazal and GitHub
390171d686
delete SAVE_SCHEDULE=1 [pr] ( #7087 )
2024-10-16 07:13:20 +03:00
George Hotz and GitHub
3169cb386d
remove graph [pr] ( #7085 )
2024-10-16 11:40:07 +08:00
qazal and GitHub
fb29de6cc3
split schedule to view_left and view_right [pr] ( #7077 )
...
* split schedule to view_left and view_right [pr]
* move valid
2024-10-16 03:39:38 +03:00
qazal and GitHub
545e79969f
always record matches in viz ( #7073 )
...
* always record matches in viz
* simpler
2024-10-15 23:03:12 +03:00
nimlgen and GitHub
b025495e5c
fuzz nv vs cuda ( #7066 )
...
* fuzz nv vs cuda
* fixes
* smth
* um
* cmp the same
* dnrt
* correct gpfifo scan
* fix
2024-10-15 22:22:40 +03:00
qazal and GitHub
09de958855
move print_diff to test/helpers ( #7071 )
2024-10-15 22:00:39 +03:00
qazal and GitHub
1a45e94f5d
viz late to_json [pr] ( #7070 )
2024-10-15 21:36:45 +03:00
qazal and GitHub
52d8afde2b
new viz unittests, isolate the ctx bug ( #7069 )
...
* start new test_viz
* test_rewrite_twice
* test_rewrite_with_ctx
* add back some of the old tests
* lints
2024-10-15 18:53:56 +03:00
nimlgen and GitHub
9f00eacde5
nv tagged memory + resnet failed kernel ( #7061 )
...
* nv tagged memory
* linter
* metal fix?
2024-10-15 18:19:58 +03:00
chenyu and GitHub
2008bac6bf
use validhack logic to rewrite buffer idx ( #6740 )
...
* use validhack logic to rewrite buffer idx
saved a whopping one mod in the conv backward kernel...
* cleanup more
2024-10-14 16:47:31 -04:00
chenyu and GitHub
a99e42cf2f
clean up test_uop_symbolic.py ( #7058 )
...
enable more tests and remove dead tests
2024-10-14 15:35:58 -04:00
chenyu and GitHub
fbaab30fe3
add timing to fuzz_linearizer ( #7056 )
...
and applied smaller FUZZ_MAX_SIZE. this is getting quite slow in CI
2024-10-14 11:57:41 -04:00
qazal and GitHub
0ef186d4be
scheduler internal api cleanups [pr] ( #7052 )
...
* delete external_benchmark_ast.py [pr]
* cleanup 2
* random
2024-10-14 15:56:10 +03:00
George Hotz and GitHub
f85c9ba00a
rewrite max to use cmplt + where ( #7037 )
2024-10-14 20:00:51 +08:00
geohot
b20b22a738
hotfix: add test_tiny, because many times it's what you want
2024-10-14 16:32:33 +08:00
Louis Novy and GitHub
2ac5aec66b
Fix exponential complexity in _is_padding_okay [pr] ( #7008 )
...
* preliminary test
* missed Optional
* don't check for cache during recursion
* match style from st_fixup... may be marginally faster?
* pathological test case: strongly connected DAG
* move to test_schedule as this isn't really a fusion
* oops this shouldn't be edited
* Revert "oops this shouldn't be edited"
This reverts commit 487cb027dc .
* Revert "move to test_schedule as this isn't really a fusion"
This reverts commit 48d8c550ce .
* move to test_schedule as this isn't really a fusion
* ok no more merge error funny business
2024-10-14 02:34:47 +03:00
chenyu and GitHub
bd8ecf7fd6
remove NumNode ( #7035 )
2024-10-13 16:42:19 -04:00
chenyu and GitHub
c4c806a210
generate new kernel dataset ( #7034 )
...
* generate new kernel dataset
pre req to remove NumNode
```
extra/optimization/generate_dataset.sh
gzip -k /tmp/sops
mv /tmp/sops.gz extra/datasets/
```
* fix var range in fuzz_linearizer
2024-10-13 16:19:41 -04:00
chenyu and GitHub
1a27417262
remove arbitrary multiplication case ( #7033 )
...
adds the wrongly simplified kernel in test_linearizer_failures
#7019
2024-10-13 15:06:05 -04:00
chenyu and GitHub
13575f080a
remove bitcast backward in function.py ( #7031 )
...
bitcast cannot backward
2024-10-13 10:08:27 -04:00
qazal and GitHub
13846930cd
hotfix: extract_dataset.py ( #7029 )
2024-10-13 11:18:23 +03:00