geohot/tinygrad
1
0
Fork 0
forked from tinygrad/tinygrad
Code Pull Requests Actions Activity
4,100 Commits 4 Branches 15 Tags
a35375df8564f4dfea5d31047c59c58f43417574
Commit Graph
4100 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
George HotzandGitHub a35375df85 run_schedule is so simple now (#4130) 2024-04-10 09:49:30 -07:00
geohot 86bd2eb500 hotfix: update copy_from_fd for new DiskBuffer 2024-04-10 15:41:06 +00:00
George HotzandGitHub ee457a4b20 no more underlying diskbuffer, that's just the device (#4129) 2024-04-10 08:32:25 -07:00
geohotstanandGitHub fe88591890 update onnx to 1.16.0 (#4127) 
* update

* pass tests and skip tests
 2024-04-10 11:19:13 -04:00
chenyuandGitHub 6bbbeb93ac skip a few clang test that took > 30 seconds in CI (#4126) 
* skip slow CLANG test test_train_cifar

* skip those too

* and that

* only CI

* one more
 2024-04-10 02:00:34 -04:00
George HotzandGitHub 08ddeb5685 create schedule has global vars (#4125) 
* abstractions3 is currently wishful thinking

* create_schedule_with_vars
 2024-04-09 21:42:16 -07:00
geohot 216eb235e5 hotfix: cast mnist to float 2024-04-09 19:30:03 -07:00
George HotzandGitHub fea774f669 spend 5 lines to bring mnist into the repo (#4122) 2024-04-09 19:24:57 -07:00
qazalGitHubGeorge Hotz
 		42edae8935 pickle schedules (#4114) 
* pickle schedules

* Update test_pickle.py

* Update test_pickle.py

---------

Co-authored-by: George Hotz <[email protected]>
 2024-04-09 13:47:25 -07:00
Felix KuehlingandGitHub 38ae4194a6 Fixes for ops_kfd (#4105) 
* kfd_ops: Fix GPU node discovery on NUMA systems

Ignore potentially multiple CPU NUMA nodes and any GPU nodes that are
not accessible because of device cgroups.

Signed-off-by: Felix Kuehling <[email protected]>

* kfd_ops: Format the GFX arch target name correctly

The target version in sysfs properties is a decimal representation with
two digits per component.

The format for LLVM GFX target names is a bit quirky for historical
reasons. It uses one digit for the minor version and stepping. When it
ran out of decimal digits for the stepping on gfx90X it started using
hexadecimal there. But the major version is still decimal and went
double digit in GFX10.

Make sure to parse and format it accordingly for all supported GPUs.

Signed-off-by: Felix Kuehling <[email protected]>

---------

Signed-off-by: Felix Kuehling <[email protected]>
 2024-04-09 13:21:21 -07:00
geohot 10dbf90b2c hotfix: test speed 2024-04-09 13:20:39 -07:00
George HotzandGitHub ae849d12d7 numpy device + pickle it (#4120) 2024-04-09 13:19:30 -07:00
chenyuandGitHub 1ef9c50fd7 Update ssa input order and annotate types in cstyle and assembly (#4117) 
variable prefix is never optional (removed the default "t") and UOp can be optional (added the default None).
 2024-04-09 13:10:29 -04:00
geohotstanandGitHub 15f2f39658 conceptually simpler fancy index (#3335) 
* init

* add failed case

* fix: temp comment out MULACC cast

* is this right?

* add test case

* oops, forgot to get rid of temp test

* WOOOOOO TOOK OUT 2 TRANSPOSES IN GATHER YAY

* cleaner

* comment cleanup

* update docs

* resolve conflict

* oops

* SUPA FAST

* comment out a test

* del some print statements

* use new broadcast stuff

* more clean up

* move try except

* skip fancy indexing for python backend test_ops
 2024-04-09 11:18:04 -04:00
David González MartínezandGitHub 980124a605 add lerp operation to tensor (#4102) 
* feat: add lerp operation to tensor

* fix

* style: fit in one line:

* tests: test backward for lerp
 2024-04-08 17:03:27 -07:00
Francis LamandGitHub 46850a0269 search: add a BEAM_COMPARE env to optionally not compare to hc/tc (#4107) 
* search: add a BEAM_COMPARE env to optionally not compare to hc/tc

setting BEAM_COMPARE=0 will prevent additional memory allocation
needed to do the timing tests assuming the BEAM result is in
the diskcache.

* change to optionally use Buffer.allocate
 2024-04-08 18:54:01 -04:00
qazalandGitHub c390828f61 refactor outbufs (#4112) 2024-04-08 14:54:10 -07:00
andresgitGitHubchenyu
 		7fd12aba85 graph remove input buffer references (#4100) 
Co-authored-by: chenyu <[email protected]>
 2024-04-08 16:49:16 -04:00
chenyuandGitHub 078d841479 add SPLIT_REDUCEOP to disable reduce split (#4115) 
verify with `SPLIT_REDUCEOP=0 BIG=2 MPS=1 python3 -m pytest -rA test/test_speed_v_torch.py -k sum`. 10X slower on mac
 2024-04-08 16:31:08 -04:00
qazalandGitHub eea42d864f account for all outputs (#4113) 2024-04-08 10:04:19 -07:00
chenyuandGitHub dbd39ab78a setitem support setting python const (#4111) 2024-04-08 11:37:50 -04:00
chenyuandGitHub f8dc82a8a7 use single tensor for llama kv chache (#4108) 
similar to optimization in gpt2
 2024-04-08 00:38:32 -04:00
chenyuandGitHub 92c0675ccf setitem initial support (#4093) 
* wip setitem

it's an eager assign to output shapetracker view

* cleanups and tests

* more cleanups
 2024-04-07 20:35:22 -04:00
geohotstanandGitHub 183708b3fd broadcast expand to match torch (#4085) 
* initial version

* heh gimme grrrreen

* version 2

* clean ups

* some test confusion

* fix onnx

* rename to _broadcast_tensors

* improved errors and test

* fixed?

* some test fixup

* version 3 lol

* comments

* cleaner

* add failure test for expand to 0 test

* 1 more assertRaises test

* make err msg better

* also rewrite the expand onnx op? :s
 2024-04-07 16:23:13 -04:00
uuuvnandGitHub 2b81d9b334 Fix broken test (#4104) 2024-04-07 12:02:12 -04:00
chenyuandGitHub 9a95d87366 metal CI run llama with 4 shards (#4103) 
this can catch multi tensor issue on mac.
 2024-04-07 11:04:08 -04:00
geohot 444d2a7487 hotfix: fix SDMA read_pointer_address in KFD 2024-04-07 13:13:15 +00:00
uuuvnandGitHub bb7567b365 Fix metal (#4101) 2024-04-07 05:21:19 -07:00
chenyuandGitHub bdbcac67f1 assign jit test case with other tensor as input (#4098) 
hmm it works
 2024-04-06 14:41:14 -04:00
George HotzandGitHub e4a1858471 revert command queue (#4097) 2024-04-06 08:58:18 -07:00
George HotzandGitHub 97c402d69e use imagenet spawn (#4096) 2024-04-06 08:34:10 -07:00
George HotzandGitHub fffd9b05f5 mock mnist data for imagenet trainer (#4095) 
* mock mnist data for imagenet

* move print and test

* needed to reshape
 2024-04-06 08:08:40 -07:00
George HotzandGitHub 8739d33fe9 kfd: disable copy_from_fd while debugging (#4091) 
* kfd: disable copy_from_fd while debugging

* increase timeout to a minute
 2024-04-05 18:02:58 -07:00
George HotzandGitHub 93824e59eb support MOCKDATA=1 for resnet (#4090) 
* mockdata for resnet

* fix eval, revert hsa
 2024-04-05 17:19:18 -07:00
George HotzandGitHub 164329a8ea address kfd feedback (#4087) 
* address kfd feedback

* signals cleanup

* signals cleanup

* handle 2 doorbell pages correctly

* signal reset cleanup

* signals cleanup

* more GTT

* cleanups

* minor cleanups
 2024-04-05 15:24:41 -07:00
geohotstanGitHubchenyu
 		dafa42e864 clean up (#4081) 
Co-authored-by: chenyu <[email protected]>
 2024-04-05 11:57:44 -04:00
Akshit TalwarandGitHub 750ecf8fef replace slice by pad/shrink in _pool (#4082) 2024-04-05 11:47:22 -04:00
George HotzandGitHub a337922c44 more work on kfd (#4079) 
* more work on kfd

* fix multitensor test on kfd

* stuff
 2024-04-05 08:36:36 -07:00
chenyuandGitHub e7ff5102cf failed test in test_pattern_matcher (#4080) 
something about the PTX rewrite is incorrect that it has duplicated rewritten uops
 2024-04-05 02:53:50 -04:00
chenyuandGitHub a023a1ed87 update github action to actions/cache@v4 (#4077) 
get rid of warning `Node.js 16 actions are deprecated. Please update the following actions to use Node.js 20: actions/cache@v3.`
 2024-04-04 22:24:26 -04:00
geohot 28ec6c67be hotfix: hlb_cifar KFD works 2024-04-05 02:19:14 +00:00
chenyuandGitHub 1de9778949 import Buffer and BufferOption from tinygrad.buffer (#4076) 2024-04-04 22:12:23 -04:00
chenyuandGitHub 9e0ebf8979 remove dtype from FlopCounter (#4075) 
the annoying thing to remove all FlopCounter is that for device that does not support local, matmul index alu is huge.
we can remove the dtype first.

sneak in updating `ruff` command to `ruff check`
 2024-04-04 21:23:28 -04:00
George HotzandGitHub 3de855ea50 don't use SVM memory in KFD (#4072) 
* don't use SVM memory in KFD

* copy from fd

* cleanups

* transfer

* hacks

* ops_hsa

* tighter API
 2024-04-04 17:33:21 -07:00
chenyuandGitHub 5e6e6c9a67 use ConstType in various const function type hint (#4074) 2024-04-04 20:32:07 -04:00
chenyuandGitHub c1cffed1df add LazyOp.dtype (#4073) 
an inferred cached_property.
removed all cases that use get_lazyop_info just to get the dtype of an op.
prereq to remove InterpretedFlopCounter
 2024-04-04 17:38:19 -04:00
chenyuandGitHub f836d6a03f is_unrealized_unpadded_const -> is_unrealized_unmasked_const (#4071) 
realized #3580 was doing the same thing. unmasked is more accurate
 2024-04-04 14:25:17 -04:00
Szymon OżógandGitHub 82b7b9655f test for dtype set (#4069) 2024-04-04 11:24:33 -04:00
geohotstanandGitHub 1a1dd1c1a7 add and enable tests for indexing const folding (#4068) 
* enable test in test_indexing

* added tests

* rename stuff

* del a test case cuz it's loadops.copy
 2024-04-04 10:46:28 -04:00
Szymon OżógandGitHub ba118abfec improved caching for pointer arithmetics in ptx (#3922) 
* improved caching for pointer arithmetics

* Add test for pointer arithmetics caching

* Refactor test
 2024-04-04 07:33:48 -07:00