Commit graph

13,661 commits

Author SHA1 Message Date
George Hotz
7a214c4499
Merge branch 'master' into clean_load 2026-06-19 16:56:57 -07:00
Christopher Milan
b2199c54a3
ci: update actions/cache/restore to suppress warnings (#16680) 2026-06-19 18:27:52 -04:00
Christopher Milan
1822eed8d3
ci: only test models on cpu (#16678) 2026-06-19 18:16:59 -04:00
wozeparrot
bba611bb59
gemm: fix mxfp8 on more shapes (#16677) 2026-06-19 13:28:53 -07:00
chenyu
67c3e589a1
invalid clone tests and prereq [PR] (#16675) 2026-06-19 13:20:43 -04:00
George Hotz
649971f02a
remove DEFINE_LOCAL and DEFINE_REG (gpt) (#16673)
* remove define_local and define_reg (gpt)

* fix precommit

* cleanups

* regalloc fix

* cleanups 2
2026-06-19 10:07:50 -07:00
George Hotz
b05bea81ce
x86 cleanups (fable) [pr] (#16591)
* x86 cleanups (fable)

* support shrink

* remove ptr dtype

* move that

* is_lane helper

* Revert "is_lane helper"

This reverts commit ea4571254d.
2026-06-19 09:04:51 -07:00
nimlgen
97c2e7a3d9
spec: add getaddr (#16674) 2026-06-19 15:37:33 +03:00
George Hotz
d7b10c69bc
update placeholder to not create DEFINE_LOCAL/DEFINE_REG (#16671)
* update placeholder to not create DEFINE_LOCAL/DEFINE_REG

* simpler

* define_local
2026-06-18 21:21:06 -07:00
Christopher Milan
091ec8d10d
use tinygrad.llm in benchmarks (#16670) 2026-06-19 00:03:57 -04:00
George Hotz
3e16109eb6 okay w/e 2026-06-18 21:00:36 -07:00
George Hotz
f79a7fc7c6
Merge branch 'master' into clean_load 2026-06-18 20:54:45 -07:00
George Hotz
3526f8272b a few fixups 2026-06-18 20:53:30 -07:00
George Hotz
925c49ce99
use placeholder in tests (#16672) 2026-06-18 20:51:44 -07:00
George Hotz
e143904deb cleanup loads 2026-06-18 18:24:59 -07:00
wozeparrot
05249466ed
llama: fused quantize mxfp8 (#16667) 2026-06-18 16:02:28 -07:00
George Hotz
4a4b6956df
remove DEFINE_VAR from codebase (gpt) (#16666)
* remove DEFINE_VAR from codebase

* junk

* remove junk
2026-06-18 15:33:50 -07:00
nimlgen
eda0a402d1
hcq2: fix multi (#16661) 2026-06-18 22:56:49 +03:00
George Hotz
5989d0b150
remove DEFINE_VAR try 2 (#16651)
* remove DEFINE_VAR try 2

* param

* null index

* fix fuzzing

* fixes

* no gather neg params

* param is just Irreducible

* fixes

* skip stack

* need to filter slots there
2026-06-18 12:34:25 -07:00
wozeparrot
d37248c3ec
gemm: fix mxfp8 on odd shapes (#16664) 2026-06-18 12:03:59 -07:00
chenyu
d74f488376
clean up _function.depth properly [PR] (#16663) 2026-06-18 14:10:22 -04:00
chenyu
d7a1022188
minor function.py cleanups [PR] (#16662) 2026-06-18 13:36:48 -04:00
qazal
924bece1d5
remove some old scheduler tests (#16660) 2026-06-18 22:15:00 +09:00
qazal
b753fb5e4c
viz: view source working even if compile failed (#16657)
* failing test

* hard

* ret_dict

* switch to _data for tests too

* update sqtt

* start work

* Ops.LINEAR looks good

* baseline with depth works

* support depth

* types

* @needs_tracked_pm

* update, marg can error too

* unwrap_or goes to many more places

* move things to soft_err

* soft_err everywhere needed

* diff cleanup

* use list

* rewrite it

* change

* update depth number

* small comment change
2026-06-18 17:34:53 +09:00
qazal
31094a794f
viz: data not sent to client side starts with _ (#16659)
* ret_dict

* switch to _data for tests too

* update sqtt

* rename to filter_keys

* not cfg
2026-06-18 15:25:22 +09:00
qazal
1720987dc7
include exception name in Ops.REWRITE_ERROR (#16658) 2026-06-18 14:52:48 +09:00
wozeparrot
bed0c343a3
faster mxfp8 gemm (#16656) 2026-06-17 22:35:36 -07:00
Christopher Milan
e0fe6e542e
ci: fewer pydeps (#16654) 2026-06-17 22:52:14 -04:00
chenyu
a74b7130b4
Revert "invalid clone try 2 [PR] (#16648)" (#16653)
This reverts commit 1bd4551ee1.
2026-06-17 22:05:30 -04:00
chenyu
df015ad541
remove many type ignores [PR] (#16652) 2026-06-17 21:38:45 -04:00
chenyu
1bd4551ee1
invalid clone try 2 [PR] (#16648) 2026-06-17 19:44:35 -04:00
George Hotz
53a1226a49
STACK 0 is dtype void (#16650)
* STACK 0 is dtype void

* spec for stack

* fix gemm group + END shape

* bump
2026-06-17 16:28:32 -07:00
George Hotz
aef85ddc4d
addrspace special/range (#16647)
* addrspace special/range

* just include indexing

* define var is alu

* bring old ignore indexing back

* mults to fix

* fixes

* ALU

* fixes
2026-06-17 15:57:37 -07:00
chenyu
1e08c0a07c
remove NOOP from AFTER with multiple srcs (#16646) 2026-06-17 14:35:02 -04:00
chenyu
1acc40600d
indexing an after with all fully invalid stores is invalid (#16643)
* indexing an after with all fully invalid stores is invalid

* typing cast
2026-06-17 11:06:36 -04:00
nimlgen
0f0c622086
hcq2: multi folders (#16642) 2026-06-17 15:20:25 +03:00
George Hotz
be9b570cb2
late numbering of var params (#16640)
* do_number_param

* fix sort order in x86

* we don't want this
2026-06-17 00:36:08 -07:00
qazal
c7055d658f
viz: only store kernel info (#16641) 2026-06-17 16:21:57 +09:00
George Hotz
d631716858
remove const without STACK (#16639)
* remove const without STACK

* fix GEP rewrite

* fix null tests

* fix openpilot regression

* it's 10 in CI
2026-06-16 21:25:42 -07:00
wozeparrot
36f6d1b064
gemm: fix bf16 atb for mp sharding (#16637) 2026-06-16 15:58:47 -07:00
qazal
1cb6b88d37
viz: show contents of vconst (#16636)
* failing test

* render vconst

* simpler test

* reorder
2026-06-17 02:31:03 +09:00
nimlgen
5644605d92
hcq2: pack bufs (#16635)
* hcq2: pack bufs

* x
2026-06-16 18:58:16 +03:00
chenyu
d5d59a2be6
remove dead rangeify rules [PR] (#16634) 2026-06-16 10:03:08 -04:00
chenyu
f0998e9bba
Revert "invalid clone is anonymous buffer" (#16613) (#16633) 2026-06-16 08:27:48 -04:00
qazal
7d2b0b697d
simple failing test for invalid extra E kernel (#16632)
* simple failing test for invalid extra E kernel

* 6 kernels
2026-06-16 17:57:44 +09:00
wozeparrot
70cac72781
llama: realize weight init (#16623) 2026-06-15 23:00:19 -07:00
Christopher Milan
443f976305
fix buffer overrun in dcache_flush (#16630) 2026-06-15 23:26:32 -04:00
chenyu
aa2bef24a8
no_vectorized_alu in cstyle does nothing now [PR] (#16631) 2026-06-15 23:07:20 -04:00
chenyu
efd03d7153
invalid clone is anonymous buffer [PR] (#16613) 2026-06-15 20:14:26 -04:00
nimlgen
4a0488ae97
hcq2: optims (#16624)
* hcq2: optims

* x
2026-06-15 23:58:28 +03:00