github/tinygrad
1
1
Fork 0
mirror of https://github.com/tinygrad/tinygrad.git synced 2026-01-10 07:28:15 -05:00
Code Issues Packages Projects Releases Wiki Activity
9,054 Commits 203 Branches 13 Tags
346b8542dace73ab6475c176a0334baa20abb768
Commit Graph

9054 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
nimlgen
346b8542da nv: fix inval from gpu_get_id_info_v2 (#10670) 2025-06-07 00:54:32 +03:00
chenyu
bdede4924e fix odd number in get_test_global_size (#10671) 
factor might not be a integer if input global_size has an odd number in it
 2025-06-06 17:31:35 -04:00
George Hotz
bf4ffc054c mstack replaces scheduler complexity (#10654) 
* mstack replaces scheduler complexity

* leave that one

* contiguous

* work

* upd

* minimal failing test

* simpler

* attention is broken

* fix transformer

* failing tests

* real fix for llama

* kv cache test

* jit multi assign test

* better tests

* comment

* fix jit issue

* traverse after buf_uop
 2025-06-06 11:31:41 -07:00
George Hotz
7f0f97aa76 new test_multitensor tests (#10667) 
* new test_multitensor tests

* cleanup scheduler
 2025-06-06 10:26:28 -07:00
qazal
5170f387b3 remove UOp.metaop [pr] (#10664) 
* little simpler UOp.const_like [pr]

* remove UOp.metaop

* bind

* remove

* min diff

* that comment is fine
 2025-06-06 16:21:48 +03:00
chenyu
4a6d84c4c3 hotfix llama start_pos vmax is max_context-1 (#10659) 
* hotfix llama start_pos vmax is max_context-1

fixed `IGNORE_OOB=0 python3 examples/llama3.py --size 1B --benchmark --temperature 0`

* hotfix: multitensor transformer test tests kv cache

---------

Co-authored-by: George Hotz <geohot@gmail.com>
 2025-06-06 00:41:25 -04:00
George Hotz
5eb6e1e65a Revert "hotfix: multitensor transformer test tests kv cache" 
This reverts commit ad9f88419a.
 2025-06-05 21:15:34 -07:00
George Hotz
ad9f88419a hotfix: multitensor transformer test tests kv cache 2025-06-05 21:08:57 -07:00
George Hotz
8325c4f192 tests for multi assign (#10658) 
* tests for multi assign

* transformer tests

* add that assert
 2025-06-05 20:56:40 -07:00
wozeparrot
0d86f8d375 fix failed threefry (#10646) 2025-06-05 17:17:42 -07:00
chenyu
e67642d430 update doc example for multinomial (#10657) 
also added many `s` for consistency
 2025-06-05 20:16:52 -04:00
Eitan Turok
61352b8aa2 Add some more docs (#10634) 
* more docs

* Add multinomial to ops

* better doc
 2025-06-05 19:40:37 -04:00
qazal
884b6cf288 remove gbarrier on const (#10656) 2025-06-06 02:36:52 +03:00
chenyu
ff1aad7b69 fix const float pow to int tensor (#10655) 
was incorrectly casted into int
 2025-06-05 19:15:12 -04:00
George Hotz
6619f17e26 force store to be contiguous (#10652) 2025-06-05 15:42:54 -07:00
wozeparrot
37e1ef1be3 feat: cleanup old AM processes (#10653) 2025-06-05 15:41:00 -07:00
George Hotz
baba274a76 minimal mstack pr to fix allreduce (#10649) 
* minimal mstack pr to fix allreduce

* fix webgpu
 2025-06-05 15:14:53 -07:00
George Hotz
4c315f8e17 MSTACK little non-functional changes (#10648) 2025-06-05 13:20:22 -07:00
b1tg
79d04d1baf AMD_LLVM: support mfma for mi300x (#10625) 
* amd llvm: support mfma for mi300x

* don't pass self

* refactor wmma render

* arch as lambda arg

---------

Co-authored-by: b1tg <b1tg@users.noreply.github.com>
 2025-06-05 15:55:44 -04:00
chenyu
46811d0d3c minor external_model_benchmark cleanup (#10644) 2025-06-05 14:13:28 -04:00
qazal
26afbc954f delete redundant tests from test_schedule [pr] (#10643) 2025-06-05 20:08:39 +03:00
chenyu
80ebce421d remove metal buffer limit in external_model_benchmark [pr] (#10642) 
not needed anymore
 2025-06-05 13:00:51 -04:00
qazal
28c4997236 check for matching shape order in fused reduce (#10641) 
* failing test

* shapes match with ones removed
 2025-06-05 19:37:22 +03:00
qazal
1190062812 prevent grouper can_chase while fusing arange [pr] (#10623) 2025-06-05 18:50:21 +03:00
uuuvn
69f7778985 refactor renderer launch bounds [pr] (#10617) 2025-06-05 08:38:04 -07:00
qazal
8c5ea00522 push permutes through fused reduces (#10628) 
* fix pushing reshapes through reduceops

* reduceop_view_right should assert on ndims mismatch

* update that, view.reshape asserts it
 2025-06-05 16:14:04 +03:00
qazal
8db0ba1161 simpler swizzle_reducop + comments [pr] (#10638) 2025-06-05 13:54:49 +03:00
qazal
ed37f29184 remove unused lib directory from viz setup [pr] (#10639) 2025-06-05 13:54:31 +03:00
chenyu
f6d7db25b7 simpler unbind_view [pr] (#10636) 2025-06-05 01:03:27 -04:00
chenyu
d0969f5a1f cleanup multi tests (#10635) 2025-06-05 00:28:44 -04:00
qazal
571c0296a9 linearizer failure from FUSE_ARANGE default diff (#10629) 
* start with test_arange_sum

* test_arange_avgpool2d

* device.renderer.supports_float4
 2025-06-04 19:11:52 +03:00
qazal
5056d21b29 add failing TestSchedule.test_arange_sum [pr] (#10627) 2025-06-04 17:23:59 +03:00
gill
9acaa6bc9a Fix button layout in viz UI for safari (#10621) 
Co-authored-by: Utkarsh Gill <engelbart@Utkarshs-MacBook-Pro.local>
Co-authored-by: qazal <77887910+Qazalin@users.noreply.github.com>
 2025-06-04 15:33:22 +03:00
Xingyu
7a1bfb668d Implement linalg_eigh function for tensor eigenvalue decomposition in torch backend (#10612) 
* Implement private _linalg_eigh function for tensor eigenvalue decomposition in torch backend

* Add unit test for linalg.eigh function in TestTorchBackend

This test verifies the eigenvalue decomposition of a 2x2 tensor using the linalg.eigh function, ensuring the computed eigenvalues and reconstructed tensor match the expected results.
 2025-06-04 07:59:50 -04:00
qazal
7114b6ab31 viz browser tests (#10626) 
* viz browser tests

* expect failure if js/ isn't included

* back green
 2025-06-04 14:58:24 +03:00
Fang-Pen Lin
b0913295d2 Add missing js files in python package data for viz (#10624) 2025-06-04 10:49:43 +03:00
wozeparrot
4d1686f767 clean: becnhmark -> benchmark (#10620) 2025-06-03 19:28:18 -07:00
chenyu
18e9ec3ea1 add wino cifar to search benchmark (#10615) 
* add wino cifar to search benchmark

* FUSE_OPTIM=1

* revert those
 2025-06-03 20:38:43 -04:00
Bhavya Gada
bafd0c30d7 fix some minor typos and grammar (#10619) 2025-06-03 15:55:25 -07:00
nimlgen
4381b54543 am: disable page migration (#10608) 
* am: disable page migration

* fixed

* enable

* fxi

* typ

* fix check
 2025-06-03 18:51:28 +03:00
chenyu
1c1f578490 DISABLE_COMPILER_CACHE in sdxl search (#10614) 2025-06-03 09:22:25 -04:00
qazal
ce9f12dc13 reorder cast before masking constants (#10609) 
* failing test from fuzzer

* .numpy() handles bfloat16 better

* const->view->cast becomes const->cast->view

* update TestMovedConstFolding.test_cast_padded
 2025-06-03 15:44:03 +03:00
qazal
910cabb081 add kernel count to grouper process replay differ [pr] (#10611) 2025-06-03 15:21:27 +03:00
chenyu
26dee71bc1 hotfix don't overwrite acc dtype in scatter_reduce (#10606) 
dtype is inferred by individul reduce
 2025-06-02 21:17:01 -04:00
ihar
ba02a6331e removed unnecessary 'isinstance(data, UOp)' check (#10605) 2025-06-02 20:58:14 -04:00
nimlgen
07de095b27 am: more info on PFs (#10602) 
* am: more info on PFs

* fix
 2025-06-02 23:48:40 +03:00
qazal
b8fb2ba829 rename to finalize_gbarrier [pr] (#10596) 2025-06-02 12:55:31 +03:00
Ahmed Harmouche
650404a143 [webgpu] Proper shared mem size for packed types (#10585) 
* Proper shared mem size in webgpu

* Add test

* Refactor test
 2025-06-01 20:18:33 -04:00
qazal
00822603ec allow stacking of VIEW UOps [pr] (#10532) 
* allow stacking of VIEW UOps [pr]

* merge_views is first

* simpler

* loc for pr, this needs a helper

* keep

* diff [pr]

* formatting
 2025-06-01 23:27:04 +03:00
qazal
3cc73a0172 simpler process replay main loop [pr] (#10588) 
* simpler process replay main loop [pr]

* use logging

* default to 1
 2025-06-01 15:03:21 +03:00