Commit Graph
13485 Commits
Author SHA1 Message Date
qazalandGitHub 854eac09c6 llama: no E_ copy after bf16 GEMM (#16458) 2026-06-02 14:14:13 +09:00
George HotzandGitHub 7d8ed8d4d7 add store to buffer's addrspace (#16468) 2026-06-01 22:07:43 -07:00
George HotzandGitHub 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
sirhcmandGitHub 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
sirhcmandGitHub b0ecbb34d9 ci: cleanup python backend tests (#16465) 2026-06-01 20:08:05 -04:00
sirhcmandGitHub 2d0f132a3b ci: cleanup more duplicate tests (#16462) 2026-06-01 18:56:29 -04:00
wozeparrotandGitHub aab9a5a8a3 llama: allow specifying layer count (#16464) 2026-06-01 15:36:04 -07:00
chenyuandGitHub 0167401fa2 minor hcopt WHERE cleanup [PR] (#16463) 2026-06-01 17:58:38 -04:00
George HotzandGitHub 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
chenyuandGitHub 517eea5985 no CONST(DEVICE) in create_allreduce_function (#16460) 2026-06-01 17:12:34 -04:00
chenyuandGitHub 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 HotzandGitHub 556defa0f7 minor updates from vec removal (#16456) 2026-05-31 09:48:51 -07:00
Javier De JesusandGitHub 989f713c1b support negative pads in circular pad mode (#16448) 2026-05-31 09:28:45 -07:00
nimlgenandGitHub 2c2cb339e0 fix word wrap (#16450) 2026-05-30 23:21:24 +03:00
qazalandGitHub 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
wozeparrotandGitHub 6795c2d5c9 llama: zero grad this way (#16445) 2026-05-29 20:25:21 -07:00
George HotzandGitHub 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
sirhcmandGitHub c377d01491 ci: run dsp on tinygrad[testing] (#16442) 2026-05-29 21:16:56 -04:00
wozeparrotandGitHub c23652e486 llama: minimize peak init mem (#16440) 2026-05-29 18:00:37 -07:00
sirhcmandGitHub d943493b79 ci: remove duplicate op compile test (#16441) 2026-05-29 19:20:31 -04:00
chenyuandGitHub 8ac62b28e5 fix AffineGrid fusion (#16439) 2026-05-29 17:59:47 -04:00
sirhcmandGitHub ef50a49693 ci: macos dev matrix (#16436) 2026-05-29 17:40:32 -04:00
sirhcmandGitHub 434cfa96a3 ci: no fetch in backend tests (#16438)
should make for less actions cache thrashing
2026-05-29 17:11:16 -04:00
chenyuandGitHub b7280705a7 limit CONST(UNIQUE) to invalids only (#16432) 2026-05-29 16:02:06 -04:00
George HotzandGitHub 9506b78d73 fix viz addrspace (#16437)
* fix viz addrspace

* revert that
2026-05-29 12:58:05 -07:00
nimlgenandGitHub d69aca41a9 hcq2: rework pm_bufferize (#16431) 2026-05-29 22:09:52 +03:00
George HotzandGitHub e2a0434403 full derivation of addrspace (#16433)
* full derivation of addrspace

* w/e, it fixes it
2026-05-29 11:39:31 -07:00
wozeparrotandGitHub 6787de9f52 llama: fix mp (#16434) 2026-05-29 11:21:43 -07:00
chenyuandGitHub 2d7e5baab4 remove vec= from UPat.cvar [PR] (#16430) 2026-05-29 10:52:30 -04:00
chenyuandGitHub fa666cefe8 remove dead branch in UOp [PR] (#16429) 2026-05-29 10:38:49 -04:00
qazalandGitHub 81bc00c006 do not require clearing method_cache in viz tests (#16428)
* update

* update test_dedup
2026-05-29 18:12:34 +09:00
qazalandGitHub 54cfb794b8 viz: addrspace little colored box (#16427)
* return addrspace

* layout

* render

* addrspace encodes color

* update colors

* in input_ast all are params are green

* update stroke
2026-05-29 17:25:07 +09:00
qazalandGitHub 814d414f41 viz: set label offset for asm (#16426) 2026-05-29 13:16:34 +09:00
wozeparrotandGitHub f86966af56 llama: optim amax margin (#16425) 2026-05-28 20:18:11 -07:00
sirhcmandGitHub 6e0d5262dc ci: autocancel outdated pr jobs (#16424) 2026-05-28 23:14:35 -04:00
sirhcmandGitHub 69aa2054f6 rename clangjit to clang (#16423) 2026-05-28 22:41:58 -04:00
sirhcmandGitHub a909acb882 move llvmspeed to benchmarks (#16422) 2026-05-28 22:26:22 -04:00
George HotzandGitHub 1e7f1dcf49 add ParamArgs [pr] (#16421)
* add ParamArgs

* fix export

* cleanups

* fixes

* simpler
2026-05-28 19:17:17 -07:00
sirhcmandGitHub 7d38edffdb ci: dev matrix (#16420)
windows just runs test_tiny
2026-05-28 22:04:04 -04:00
wozeparrotandGitHub 36c8ff70c1 llama: use old scale for dequant in optim (#16417) 2026-05-28 15:21:19 -07:00
c87f3433d1 use namespace runners (#16387)
Co-authored-by: Christopher Milan <[email protected]>
2026-05-28 18:05:46 -04:00
George HotzandGitHub c9adde72c1 addrspace property (#16418)
* addrspace property

* movement addrspace

* regs
2026-05-28 14:39:25 -07:00
sirhcmandGitHub c8af163d2b disable process replay by default (#16419)
enable process replay with [pr] and assert with [PR]
process replay no longer captures on master
2026-05-28 17:36:28 -04:00
nimlgenandGitHub b0e49afaf1 hcq2: new multi (#16413)
* hcq2: new multi

* op
2026-05-28 22:16:10 +03:00
George HotzandGitHub edca5df25a flip offset and shape in pad and shrink (#16414)
* flip offset and shape in pad and shrink

* dumb test
2026-05-28 11:58:19 -07:00
chenyuandGitHub d72d8ee065 .const() should not ignore dtype (#16412)
fixed a bug in postrange, also cleaner
2026-05-28 10:49:15 -04:00
sirhcmandGitHub 0ae957bb0a refactor webgpu (#16406) 2026-05-27 23:13:08 -04:00
qazalandGitHub 202adc644e viz: make call toggle easier to click on (#16411)
* call tag is a rect

* details

* colors

* simplify, better comment
2026-05-28 11:53:36 +09:00
George HotzandGitHub 5ee6b6b79e fix slice store to remove the index (#16410)
* fix slice store to remove the index

* fix spec
2026-05-27 19:17:53 -07:00
qazalandGitHub 88e88d63d6 viz: click on +- toggles sources (#16409) 2026-05-28 09:12:43 +09:00