qazal and GitHub
3b1a5f9770
llama: a_bT and aT_b bf16 gemms ( #16487 )
...
* hk_bf16_gemm
* enable in 8b
* cleanups
* rename to USE_HK_BF16_GEMM
* work
* work
* work
* work
* change the gemms
* work
* work
* set as default
* work
* change
2026-06-04 23:30:21 +09:00
chenyu and GitHub
5fad87252d
no device= into arange and eye ( #16503 )
2026-06-04 09:21:50 -04:00
nimlgen and GitHub
11af81f96f
hcq2: cleaner ( #16502 )
2026-06-04 15:26:37 +03:00
chenyu and GitHub
2c915c61ed
no CONST(DEVICE) in torch_backend ( #16499 )
2026-06-04 00:26:47 -04:00
wozeparrot and GitHub
fd13080636
deviceless const skip axis check ( #16496 )
2026-06-03 19:13:20 -07:00
qazal and GitHub
f7f03bd7e5
viz: better name for src id in kernel_graph.txt ( #16495 )
...
* viz: better name for src id in kernel_graph.txt
* better order
* cleanup
2026-06-04 11:09:29 +09:00
sirhcm and GitHub
9dac781e45
ci: use uv ( #16492 )
2026-06-03 21:38:50 -04:00
George Hotz and GitHub
9fdeaa402b
no anon addrspace, don't write hacks ( #16491 )
...
* no anon addrspace, don't write hacks
* revert that
* no reg there
2026-06-03 16:19:30 -07:00
chenyu and GitHub
2f83d01ccf
fix deviceless materialize device ( #16493 )
...
symbolic arange currently does not fuse, which creates a deviceless UOp post rangeify that needs a device to bufferize
2026-06-03 19:13:21 -04:00
chenyu and GitHub
19eb72ff60
remove use of full with buffer=False and non-None device= ( #16489 )
2026-06-03 16:21:24 -04:00
nimlgen and GitHub
6f2a2857c8
hcq2: refactor deps ( #16490 )
2026-06-03 23:20:24 +03:00
chenyu and GitHub
243446b44f
remove CONST(DEVICE) from const_like ( #16488 )
2026-06-03 14:04:51 -04:00
George Hotz and GitHub
cee472a0ef
renderer Estimates uses maxel ( #16485 )
2026-06-03 10:55:00 -07:00
chenyu and GitHub
8a4203638a
make full with buffer=False deviceless ( #16483 )
...
affects arange and eye
2026-06-03 12:35:59 -04:00
qazal and GitHub
405866f2b7
viz: improve kernel_graph.py usability ( #16486 )
...
* better default
* always format kernel output
* also show ref
* sched num
2026-06-03 21:12:44 +09:00
sirhcm and GitHub
f43cba5765
ci: native python where possible ( #16473 )
...
linters stays at 3.11
2026-06-02 22:40:12 -04:00
wozeparrot and GitHub
7dcfd144b6
llama: columnwise fp8 scaling ( #16480 )
2026-06-02 18:55:45 -07:00
George Hotz and GitHub
ffadd7a315
remove intel and amx support ( #16482 )
2026-06-02 18:53:05 -07:00
George Hotz and GitHub
5f439e3b7c
refactor cstyle to avoid dtype [PR] ( #16478 )
...
* refactor cstyle to avoid dtype
* clean up rules
* add new style option
2026-06-02 18:27:12 -07:00
sirhcm and GitHub
80eeb4dd21
mockgpu: use autogen.libc ( #16479 )
2026-06-02 19:59:36 -04:00
chenyu and GitHub
a43b55d480
deviceless const folding schedule test ( #16477 )
2026-06-02 18:46:30 -04:00
George Hotz and GitHub
14f843737b
renderer cleanups (pt 3) [PR] ( #16475 )
...
* renderer cleanups (pt 3)
* point refactors
* fix bugs
* fix PR
2026-06-02 14:24:24 -07:00
nimlgen and GitHub
99e37b1ee3
hcq2: deps ( #16459 )
...
* start
* sin
* f
2026-06-02 22:34:25 +03:00
George Hotz and GitHub
82f1c983d4
clean renderer migrations [pr] ( #16472 )
...
* clean renderer migrations
* minor webgpu
* use PARAM UOp as API
* make linter happy
2026-06-02 11:19:00 -07:00
sirhcm and GitHub
9897658895
ci: fix ocelot compilation on macos ( #16471 )
2026-06-02 12:43:31 -04:00
chenyu and GitHub
6b7d2b91df
update test_uop_graph ( #16470 )
...
use UOp methods instead of constructing UOp directly, some of it violated spec
2026-06-02 08:53:54 -04:00
qazal and GitHub
854eac09c6
llama: no E_ copy after bf16 GEMM ( #16458 )
2026-06-02 14:14:13 +09:00
George Hotz and GitHub
7d8ed8d4d7
add store to buffer's addrspace ( #16468 )
2026-06-01 22:07:43 -07:00
George Hotz and GitHub
20242fdf1d
update test + spec from shrink_in_render ( #16467 )
...
* update test + spec from shrink_in_render
* cast
2026-06-01 19:24:43 -07:00
sirhcm and GitHub
c6cad1ad67
ci: standardize runs-on ( #16466 )
...
* ci: use macos 26
* ugh github
* stick with github for arm
2026-06-01 21:39:58 -04:00
sirhcm and GitHub
b0ecbb34d9
ci: cleanup python backend tests ( #16465 )
2026-06-01 20:08:05 -04:00
sirhcm and GitHub
2d0f132a3b
ci: cleanup more duplicate tests ( #16462 )
2026-06-01 18:56:29 -04:00
wozeparrot and GitHub
aab9a5a8a3
llama: allow specifying layer count ( #16464 )
2026-06-01 15:36:04 -07:00
chenyu and GitHub
0167401fa2
minor hcopt WHERE cleanup [PR] ( #16463 )
2026-06-01 17:58:38 -04:00
George Hotz and GitHub
124d2f8227
anon addrspace from new renderer ( #16461 )
...
* anon addrspace from new renderer
* use max_numel in python renderer
* add sizes to ptrs in tests
* more
* correct fix
2026-06-01 14:42:02 -07:00
chenyu and GitHub
517eea5985
no CONST(DEVICE) in create_allreduce_function ( #16460 )
2026-06-01 17:12:34 -04:00
chenyu and GitHub
7e7b481ba7
less CONST(DEVICE) ( #16452 )
...
* less CONST(DEVICE)
no DEVICE for single device in const_like, multi has other issues
* maybe
* that?
2026-06-01 15:55:12 -04:00
George Hotz and GitHub
556defa0f7
minor updates from vec removal ( #16456 )
2026-05-31 09:48:51 -07:00
Javier De Jesus and GitHub
989f713c1b
support negative pads in circular pad mode ( #16448 )
2026-05-31 09:28:45 -07:00
nimlgen and GitHub
2c2cb339e0
fix word wrap ( #16450 )
2026-05-30 23:21:24 +03:00
qazal and GitHub
29b47a0057
llama: update local amax implementation after ParamArgs change ( #16446 )
...
* local amax failing test
* update _local_abs_max_fxn
2026-05-30 16:55:43 +09:00
wozeparrot and GitHub
6795c2d5c9
llama: zero grad this way ( #16445 )
2026-05-29 20:25:21 -07:00
George Hotz and GitHub
cf55aaf01f
python prg is pkl uops ( #16443 )
...
* python prg is pkl uops
* refactor to use uop
* refactor to u.
2026-05-29 19:13:51 -07:00
sirhcm and GitHub
c377d01491
ci: run dsp on tinygrad[testing] ( #16442 )
2026-05-29 21:16:56 -04:00
wozeparrot and GitHub
c23652e486
llama: minimize peak init mem ( #16440 )
2026-05-29 18:00:37 -07:00
sirhcm and GitHub
d943493b79
ci: remove duplicate op compile test ( #16441 )
2026-05-29 19:20:31 -04:00
chenyu and GitHub
8ac62b28e5
fix AffineGrid fusion ( #16439 )
2026-05-29 17:59:47 -04:00
sirhcm and GitHub
ef50a49693
ci: macos dev matrix ( #16436 )
2026-05-29 17:40:32 -04:00
sirhcm and GitHub
434cfa96a3
ci: no fetch in backend tests ( #16438 )
...
should make for less actions cache thrashing
2026-05-29 17:11:16 -04:00
chenyu and GitHub
b7280705a7
limit CONST(UNIQUE) to invalids only ( #16432 )
2026-05-29 16:02:06 -04:00