sirhcm/tinygrad
1
0
Fork 0
forked from tinygrad/tinygrad
Code Pull Requests 2 Actions 8 Activity
13,187 Commits 336 Branches 15 Tags
ff1258feef92a15c0ada183bb00481db83f63db3
Commit Graph
13187 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
geohot ff1258feef fix tests 2026-05-04 17:33:01 -07:00
geohot 51b13466dd fix amd 2026-05-04 17:23:43 -07:00
geohot 416878db9e i hate ai 2026-05-04 17:14:53 -07:00
geohot e00b3b4065 fix 2026-05-04 17:09:59 -07:00
George HotzandGitHub d810bd2b41 Merge branch 'master' into move_gates_to_load_store 2026-05-04 17:05:21 -07:00
geohot 09ec34437d fix oob validation 2026-05-04 16:55:32 -07:00
chenyuandGitHub a357a0449a Tensor.div cleanup (#16041) 2026-05-04 19:27:36 -04:00
geohot 36383298be move gates to load/store 2026-05-04 14:56:37 -07:00
geohot 8f397f5c7c move load gates 2026-05-04 14:45:42 -07:00
nimlgenandGitHub 5b4f62519d cache buffer_views as well (#16039) 
* cache buffer_views as well

* reuse

* back

* x
 2026-05-05 00:00:09 +03:00
sirhcmandGitHub 8e99c4f097 fetch checks sha256 (#16037) 2026-05-04 16:08:38 -04:00
George HotzandGitHub 1884f67a39 simplify full_rewrite_to_sink spec (#16035) 
* simplify full_rewrite_to_sink spec

* test cleanups
 2026-05-04 11:44:13 -07:00
chenyuandGitHub a4fccd23b2 remove kwargs in UOp.vectorize [pr] (#16034) 2026-05-04 12:46:38 -04:00
qazalandGitHub b1d88ebf02 viz/cli: aggregate flops in -t (#16031) 
* 38

* plumbing

* more flops

* flop/s and bytes/s

* arithmetic mean

* tests

* harmonic mean

* range

* better

* simplify

* fix prints

* no string parsing needed
 2026-05-04 17:35:02 +03:00
qazalandGitHub c02e390c2b viz: encode flops, mem and metadata in json (#16032) 
* gate print

* update everywhere to check path

* server encodes json

* ui changes

* cli changes

* tests never need regex

* no str replace

* update test_pipes

* remove that
 2026-05-04 23:06:18 +09:00
bigyoshiGitHubbigyoshi51
 		4024d8438f runtime/graph: avoid core_id runtimevar merge conflicts (#16026) 
Co-authored-by: bigyoshi51 <[email protected]>
 2026-05-03 19:16:02 +03:00
qazalandGitHub 9684334dfe viz: fix flops in graph, add null graph tracing (#16024) 
* min repro, todos

* null graph tracing

* work

* work

* work

* only test_flops

* exec points back

* first

* better

* integral timestamps maybe

* cleanup

* simpler, update NULL to use SDMA naming

* integration test

* sdma
 2026-05-03 22:32:44 +09:00
wozeparrotandGitHub 419d525553 feat: handle multioutput kernel grads (#16028) 2026-05-02 22:31:45 -07:00
mefenglandGitHub 9717d3a3a2 hotfix: prepend LD_LIBRARY_PATH to DLL posix search dirs (#16023) 2026-05-02 20:45:19 +03:00
qazalandGitHub 7daf4b7d52 viz: split cli test (#16015) 
* viz: split cli test

* arg3 is msg
 2026-05-03 01:47:11 +09:00
nimlgenandGitHub d65b8ca25f jit: remove *input_list from the graph sources (#16021) 2026-05-02 14:42:47 +03:00
qazalandGitHub 7dae9e6f7f viz: keep VIZ.value = 0 during python shutdown, cleanup launch (#16022) 
* viz: keep VIZ.value = 0 during python shutdown, cleaner execv

* rm
 2026-05-02 20:35:53 +09:00
sirhcmandGitHub 637bdd5530 am: only support CDNA3/4 and RDNA3/4 (#16017) 2026-05-02 00:02:14 -04:00
George HotzandGitHub 4a2e1f1076 STORE doesn't have ranges anymore (#16019) 
* STORE doesn't have ranges anymore

* fix
 2026-05-01 15:00:27 -07:00
chenyuandGitHub 0bffbc5f8a onnx fmod uses fmod (#16018) 2026-05-01 16:47:11 -04:00
chenyuandGitHub 782d1ff80f Tensor.fmod (#16014) 
c-style mod matches torch
 2026-05-01 16:02:18 -04:00
nimlgenandGitHub 1079441332 revoke bus master (#16007) 2026-05-01 18:00:01 +03:00
qazalandGitHub 8b147a9ed5 minimal repro for llama copies 2 (#16011) 2026-05-01 22:23:47 +09:00
qazalandGitHub a29dd7b19b Revert "cleanup: untrack wait Metal buffers (#15954)" (#16010) 
* Revert "cleanup: untrack wait Metal buffers (#15954)"

This reverts commit 5eb1fd5d3c.

* regression test fixes
 2026-05-01 21:18:19 +09:00
qazalandGitHub 65879fe1b7 metal synchronize regression test (#16008) 
* add test for metal wait=True

* add self.assertRaises
 2026-05-01 20:10:57 +09:00
nimlgenandGitHub f6d92b55e6 am: use per pipe reset for gfx11+ (#16006) 2026-05-01 12:56:43 +03:00
sirhcmandGitHub cee73becbe am: ip offsets in autogen (#16003) 2026-05-01 00:13:52 -04:00
George HotzandGitHub 4506688285 split render to render.py (#16002) 
* split render to render.py

* move more print
 2026-04-30 19:41:14 -07:00
George HotzandGitHub d651b4bbf0 SPEC=3 checks the shape (#16001) 
* SPEC=3 checks the shape

* buffer view

* Revert "buffer view"

This reverts commit ffd87889a9.

* buffer view hack

* fix ptx
 2026-04-30 18:41:37 -07:00
wozeparrotandGitHub 528d35e306 llama speed 4 (#15993) 2026-04-30 17:14:41 -07:00
George HotzandGitHub 45fd7a3668 lil_image vectorize (#16000) 
* lil_image vectorize

* 0 pitch on height 1

* Revert "0 pitch on height 1"

This reverts commit 58a83e6622.
 2026-04-30 16:12:43 -07:00
wozeparrotandGitHub eddcd4723b am_smi throttle info (#15997) 2026-04-30 15:28:32 -07:00
chenyuandGitHub 52c92e15ae no replacement multinomial (#15995) 
* no replacement multinomial

Efraimidis–Spirakis

* num_samples == 1 can use fast path
 2026-04-30 17:35:26 -04:00
chenyuandGitHub e0b09f288f input validation for rand functions (#15990) 2026-04-30 14:00:44 -04:00
nimlgenandGitHub 11e1a2b89f cleaner and faster run_linear (#15987) 
* cleaner and faster run_linear

* x

* assert for now

* x

* x

* sym_infer

* remove sink
 2026-04-30 20:15:22 +03:00
qazalandGitHub 58b34e71bd failing test for llama useless copies (#15989) 2026-05-01 00:55:29 +09:00
George HotzandGitHub 0f7e296f5b fix some indexing edge cases (#15988) 2026-04-30 08:05:30 -07:00
nimlgenandGitHub 6f8b10d251 remove base Runner (#15986) 
* remove base Runner

* linters
 2026-04-30 13:04:55 +03:00
George HotzandGitHub 46a36a838a small dtype shapes fixups (#15984) 2026-04-29 19:40:38 -07:00
chenyuandGitHub b73248958a minor rand cleanups (#15982) 2026-04-29 22:22:29 -04:00
chenyuandGitHub 53a28bafbd rand device seed to its own function (#15979) 2026-04-29 17:21:40 -04:00
sirhcmandGitHub d07741f1d7 am: look for firmware in /lib/firmware/amdgpu (#15974) 2026-04-29 17:15:09 -04:00
nimlgenandGitHub c73e667fc0 remove if for precompiled programs (#15980) 2026-04-29 23:43:36 +03:00
qazalandGitHub 55915584e5 viz: fix cfg for emulated amd on the null device (#15976) 
* simple failing when i test it end to end

* pass

* linter

* assemble
 2026-04-30 05:18:09 +09:00
nimlgenandGitHub dfd2d07005 remove CompiledRunner (#15970) 
* rm usage of CompiledRunner

* more tests

* last

* linter

* sink

* remove

* linter
 2026-04-29 22:45:48 +03:00