mirrors/tinygrad
2
0
Fork 0
mirror of https://github.com/tinygrad/tinygrad.git synced 2026-06-24 02:14:17 +00:00
Code Issues Projects Releases Packages Wiki Activity
11,329 commits 280 branches 15 tags 325 MiB
Commit graph

1,578 commits

Author SHA1 Message Date
kamilisjon
e20bc0b9b5
 		remove unused function parameter in beam search (#13602) 2025-12-06 11:40:47 -05:00
chenyu
21aac568fd
 		limit lift x*y out of reduce to int [pr] (#13535) 2025-12-02 16:11:45 -05:00
George Hotz
037edc151c
 		late gate for ALLOW_TF32 (#13527) 
* remove ALLOW_TF32

* the right place to put that gate
 2025-12-02 07:51:58 -08:00
Roelof van Dijk
eb543a91e8
 		perf: remove graph-in-graph from expand_index (#13473) 
* remove graph-in-graph from devectorizer

* vectorize, not sink

---------

Co-authored-by: George Hotz <72895+geohot@users.noreply.github.com>
 2025-11-27 11:32:16 -08:00
Sieds Lykles
114bb94c55
 		Fix load collapse MAX to ADD (#13406) 
* add Ops.ADD to pattern

* add test
 2025-11-21 12:26:14 +01:00
chenyu
fa3def2f12
 		call less simplify in simplify_valid_load [pr] (#13401) 2025-11-20 19:54:22 -05:00
chenyu
647fde64e6
 		no sym in pm_reduce [pr] (#13398) 
* no sym in pm_reduce [pr]

* fix that
 2025-11-20 16:49:09 -05:00
George Hotz
225eb1500f
 		generic range changes that work for str + int (#13350) 
* generic range changes that work for str + int

* opt range counts up
 2025-11-19 08:07:49 -08:00
George Hotz
6d3385c284
 		print special ops in postrange (#13318) 
* print special ops in postrange

* fix on OSX
 2025-11-17 14:43:23 -08:00
George Hotz
6c5fa349e1
 		add (unused) outer range (#13285) 2025-11-14 16:47:52 -08:00
chenyu
58b7e4fab3
 		GROUPTOP heuristic on more axes (#13206) 
fixed dm speed
 2025-11-10 23:30:37 -05:00
chenyu
e1d46de8f8
 		update GROUPTOP heuristic more (#13178) 
reverts #13176
 2025-11-09 02:31:12 -05:00
chenyu
41e45c20ff
 		minor stuff reading the printed code [pr] (#13177) 2025-11-09 00:58:51 -05:00
chenyu
8e868dced8
 		only GROUPTOP one reduce kernel (#13176) 
* only GROUPTOP one reduce kernel

* ALLOWED_GATED_READ_IMAGE=148
 2025-11-08 22:38:44 -05:00
chenyu
a62496cb3d
 		clean up get_grouped_dims [pr] (#13159) 2025-11-08 01:53:54 -05:00
wozeparrot
eb0192b0bb
 		feat: print ranges that aren't ended (#13167) 2025-11-07 22:01:29 -08:00
chenyu
6a509da7f3
 		Scheduler.reduceops helper [pr] (#13162) 2025-11-07 18:59:46 -05:00
Ahmed Harmouche
3ecff3a8da
 		Fix dim splitting bug for len(dim) == len(limited) case (#13142) 
* Fix gpudims bug on webgpu

* Fix split dim bug

* Remove webgpu_bug from examples

* Add test for shape correctness

* Fix 3D indexing

---------

Co-authored-by: chenyu <chenyu@fastmail.com>
 2025-11-07 12:31:06 -05:00
George Hotz
bb6364d7c7
 		tuplize from linearizer behind flag (#13136) 
* remove tuplize from linearizer

* optional tuplize
 2025-11-06 20:15:03 -08:00
George Hotz
42b34cf83d
 		bottom up linearizer (#13133) 
* bottom up linearizer

* late stores

* more complete

* remove broken heuristic

* upcast size

* opt

* more conservative

* it needs that

* disable opencl half on QCOM

* fix

* make that a real test

* cpu test okay

* ptx skip

* end is after the range
 2025-11-06 15:30:32 -08:00
George Hotz
e0d828dba8 little cleanups 2025-11-06 13:58:19 -08:00
George Hotz
290441dd44
 		do loads early (#13131) 
* do loads early

* local and reg
 2025-11-06 09:57:09 -08:00
George Hotz
097264853d
 		very simple priority (#13130) 
* very simple priority

* still simple
 2025-11-06 09:25:28 -08:00
George Hotz
07b415e831
 		fixup op order (#13128) 
* fixup op order

* more order

* move a few more

* more

* DEBUG_LINEARIZE
 2025-11-06 08:50:04 -08:00
George Hotz
91cc773397
 		add run count to toposort (#13119) 2025-11-05 22:29:34 -08:00
chenyu
ca17718b6d
 		remove symbolic_flat (#13083) 
* remove symbolic_flat

some kernels are different but sometimes it's better so not clear, will merge as long as benchmark passes

* test_location
 2025-11-03 17:25:21 -05:00
George Hotz
1e3d6e49a6
 		index slicing + allclose (#13071) 
* continue work on slicing+allclose

* Revert "Revert "slicing + allclose""

This reverts commit 6c7a12f21c.

* fix tests + better syntax

* forgot an after

* slot is an integer
 2025-11-03 13:01:48 +08:00
George Hotz
6c7a12f21c Revert "slicing + allclose" 
This reverts commit c9a1e35b1e.
 2025-11-03 12:05:44 +08:00
George Hotz
c9a1e35b1e slicing + allclose 2025-11-03 12:00:45 +08:00
Sieds Lykles
885b6dea9e
 		multiple reduce range arange folding (#13047) 
* multi reduce arange folding

* add test

* cvar to var

* add circular_pad_bw test
 2025-11-01 22:11:26 +01:00
Sieds Lykles
f97fb703c8
 		catch group error in matvec heuristic (#13051) 2025-11-01 22:09:35 +01:00
George Hotz
65a0a31475
 		AMD mi350x matmul from stream (#13040) 
* works

* working mfma

* 120 TFLOPS

* regs

* 192 TFLOPS

* try pipelining

* something

* notes

* contract

* linter to 3.11

* that was a bug
 2025-11-01 17:55:19 +08:00
George Hotz
b2caf4c2b3
 		prepare for custom kernel (#13029) 2025-10-31 14:47:37 +08:00
George Hotz
b46229ca51
 		use shrink in amd_matmul_uop (#13026) 
* use shrink in amd_matmul_uop

* colors
 2025-10-31 10:43:41 +08:00
b1tg
363a201cc6
 		fp8 amd cstyle (#12999) 
* amd fp8 cstyle

* don't repeat

* space

* lint

---------

Co-authored-by: chenyu <chenyu@fastmail.com>
 2025-10-30 10:45:52 -04:00
chenyu
985b6eb95f
 		ues less typing.cast [pr] (#13002) 2025-10-30 09:29:52 -04:00
George Hotz
4a741e8364
 		modernize amd uop matmul (#13011) 
* modernize amd uop matmul

* progress

* comment

* more comments

* revert that

* mac cleanups

* fix estimates

* format
 2025-10-30 17:02:38 +08:00
qazal
66ea3a0be4
 		put DEFINE_LOCAL counter in context (#13008) 2025-10-30 15:49:26 +08:00
George Hotz
e456f2cb1e
 		more uop programs (#13007) 
* more uop program

* test_matmul_relu

* tests fix
 2025-10-30 14:57:59 +08:00
George Hotz
e64d4b3b44
 		uops programs (#13005) 
* uops programs

* work

* work

* more syntax

* more syntax

* comments
 2025-10-30 12:28:10 +08:00
George Hotz
5894df059c hotfix: prevent inf loop if reduce splits 2025-10-30 11:21:40 +08:00
George Hotz
2da02f1ae1
 		add loads at the end (#12988) 
* add loads at the end

* simpler

* late load

* tests passing

* fix matvec

* spec test passes

* fix where on load

* fix abs2

* fix more tests
 2025-10-30 10:42:19 +08:00
George Hotz
819592ee67 hotfix: disable DoubleMatmul for PTX 2025-10-29 16:37:17 +08:00
George Hotz
30ca3f2af8
 		all double matmul (#12993) 
* fix more double matmuls

* a few more

* all double matmul passes

* opts for flash attention

* fix spec

* comment
 2025-10-29 16:25:27 +08:00
George Hotz
1c362736aa
 		fix more double matmuls (#12991) 
* fix more double matmuls

* a few more
 2025-10-29 16:09:48 +08:00
George Hotz
e42b4edf8c
 		remove if stuff (#12992) 2025-10-29 15:29:35 +08:00
George Hotz
8c47cf4323
 		pcontig double matmul works (#12899) 
* pcontig double matmul works

* tests

* contract

* closer

* works-ish

* add that broadcast

* 2 more work

* something

* disable broken ones

* llvm

* align 16
 2025-10-29 13:06:43 +08:00
George Hotz
35b6f4148d
 		delete untested quantize (#12990) 2025-10-29 12:46:32 +08:00
Sieds Lykles
5ce8a1d2f2
 		Merge adjacent try all permutations for reduce (#12972) 2025-10-29 05:04:54 +01:00
chenyu
9442442cb1
 		update variable names in search [pr] (#12979) 
no lin nor linearize
 2025-10-28 15:37:52 -04:00