sirhcm/tinygrad
1
0
Fork 0
forked from tinygrad/tinygrad
Code Pull Requests 2 Actions 8 Activity
11,064 Commits 336 Branches 15 Tags
cabd4add4893e25eaab1cada44d7a89b84fcdf41
Commit Graph
11064 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
George HotzandGitHub cabd4add48 more work parsing SQTT, separate VIZ/PROFILE (#13308) 
* more work parsing SQTT

* more minimal runner

* sep VIZ/PROFILE

* parse print new

* improve parser

* more filter

* that

* split them

* lil cleanup

* skip flaky test

* AQL in mmapeak
 2025-11-16 10:40:39 -08:00
qazalandGitHub 13efdf8c31 test s_nop stall (#13307) 2025-11-17 00:59:39 +08:00
George HotzandGitHub 295600dc5a saturday coffee shop work parsing the att format (#13295) 
* saturday coffee shop work parsing the att format

* add examples

* parser

* classes of packets

* fully vibe coded parser

* vibing

* empty

* some vibe names

* vibes

* most of these are wrong

* more vibes

* better names

* parsing

* parse

* cleanup parser

* touchups
 2025-11-16 08:25:51 -08:00
sirhcmandGitHub a9ed241172 properly suppress NIRRenderer.__del__ error (#13299) 2025-11-16 18:58:04 +03:00
qazalandGitHub c70b06ec19 sqtt test_timing work (#13304) 
* sqtt test_timing cleanups

* only the instruction

* v_mfma_f32_16x16x32_f16 16 cycles, only after second one though
 2025-11-16 23:49:24 +08:00
chenyuandGitHub 8f0e747b3a Tensor._tri with arange (#13297) 2025-11-16 10:21:16 -05:00
chenyuandGitHub 6372c95094 disable benchmark MobileNetV2 on DSP (#13305) 
failed on tinyc2
 2025-11-16 09:42:52 -05:00
sirhcmandGitHub 61625a3898 fix objc finalizing bug (#13296) 2025-11-16 12:43:04 +03:00
nimlgenandGitHub acbe6361ab qcom: suppress_finalizing to free (#13294) 2025-11-16 11:49:23 +03:00
wozeparrotandGitHub ef42334239 tk: load store cleanup (#13290) 2025-11-15 17:08:23 -08:00
chenyuandGitHub e8844853ed Tensor.eye with arange (#13287) 
with rangify we can write these with arange
 2025-11-15 12:32:27 -05:00
sirhcmGitHubGeorge Hotz
 		5b823af696 Remove (pypi) clang dep for autogen (#13284) 
* no more clang

* regen comgr_3

* ci doesn't need pypi clang

* fix objc

* REGEN for libclang

---------

Co-authored-by: George Hotz <[email protected]>
 2025-11-15 09:05:11 -08:00
geohot df53c62a9f bump line count 2025-11-15 08:16:20 -08:00
nimlgenandGitHub d37e1fe065 nv: wait for wpr to reset (#13282) 
* nv: wait for wpr to reet

* fix

* comment

* wai

* f

* fix
 2025-11-15 20:00:49 +08:00
George HotzandGitHub 22c08b470c fold using outerworld range (#13286) 
* scan using outerworld range

* almost

* sched

* simple range

* mypy

* woooo outer range

* spec passes

* print the numbers

* lol it runs

* real test
 2025-11-14 20:43:41 -08:00
George HotzandGitHub 567066f51f tests for cast there and back (#13195) 
* fix cast folding in llama

* dtypes that work everywhere

* Skip test_cast_there_and_back for backend casts

Skip test due to backend casting issues.
 2025-11-14 16:56:09 -08:00
George HotzandGitHub 6c5fa349e1 add (unused) outer range (#13285) 2025-11-14 16:47:52 -08:00
sirhcmGitHubGeorge Hotz
 		d1bb08c5a1 In-tree autogen: objective c (#13223) 
* checkout changes from autogen branch

* move assert

---------

Co-authored-by: George Hotz <[email protected]>
 2025-11-14 14:08:42 -08:00
George HotzandGitHub e5351699bd openpilot warp (#13283) 
* openpilot image warp test

* 0.4 ms on metal, 1 ms on CPU

* new inputs each time

* reshape
 2025-11-14 13:55:32 -08:00
qazalandGitHub 7c110e1a57 viz: minor cleanups for sqtt (#13275) 
* small prg cleanup

* test_timing
 2025-11-15 01:08:56 +08:00
chenyuandGitHub 888aaab151 test_tiny cleanup (#13276) 2025-11-14 11:11:32 -05:00
nimlgenandGitHub 3e63831b98 nv: support 580+ drivers (#13269) 
* nv: 580+ support

* start

* f

* fake

* fix
 2025-11-14 21:44:16 +08:00
qazalandGitHub 2ee701a009 roc: fix CEnum access (#13270) 
* roc: add decoder to ci

* also add installer

* use CEnum syntax

* try 2

* add to setup

* revert ci change

* the other enum too
 2025-11-14 21:41:24 +08:00
nimlgenandGitHub c80d459d99 autogen: fix packed args structs (#13274) 
* autogen: fix packed args structs

* and test this
 2025-11-14 20:24:06 +08:00
nimlgenandGitHub 14eb48b13a autogen: rename nv_gpu to nv_570 (#13273) 
* autogen: rename nv_gpu to nv_570

* rename
 2025-11-14 20:07:19 +08:00
nimlgenandGitHub 734bfa07b4 nv: refactor uvm calls (#13272) 2025-11-14 19:53:04 +08:00
nimlgenandGitHub f72b1fbca4 nv: read numClasses (#13271) 
* nv: read numClasses

* fix

* d
 2025-11-14 19:43:25 +08:00
nimlgenandGitHub 84f065f2a2 autogen: warning and msg (#13268) 
* autogen: warning and msg

* f
 2025-11-14 19:10:26 +08:00
George HotzandGitHub 44d84228ff move comgr_3 logic back to the old place (#13266) 
* move comgr_3 logic back to the old place

* explicit
 2025-11-13 20:05:54 -08:00
sirhcmGitHubGeorge Hotz
 		09f3aae169 In-tree autogen: all C libraries (#13220) 
* checkout files from autogen branch

* ioctl with payload

* fix am generations

* properly fix generations

This reverts commit b2a54f4f41.

* revert discovery.h

* support pragma pack(1)

* typo

* better getter

* typo

* NVCEC0_QMDV05_00_RELEASE[01]_ENABLE

* align support

* anon handling fix

---------

Co-authored-by: George Hotz <[email protected]>
 2025-11-13 18:57:44 -08:00
wozeparrotandGitHub 777cbec5b3 tk: rename rt tile dims to base (#13265) 2025-11-13 18:43:02 -08:00
wozeparrotandGitHub 7eb0d8e744 feat: mixins on tiles (#13246) 2025-11-13 16:52:52 -08:00
George HotzandGitHub ba84d415fe work from benchmarking tinybox red v2 (#13264) 
* work from benchmarking tinybox red v2

* gpuburn
 2025-11-13 16:38:40 -08:00
wozeparrotandGitHub 547304c471 tk: group cleanup (#13262) 2025-11-13 14:19:51 -08:00
wozeparrotandGitHub 4ada51618f tk: don't flatten in clear (#13249) 2025-11-13 13:38:01 -08:00
George HotzandGitHub 6b1bae6614 ruff format mixin (#13261) 2025-11-13 10:10:38 -08:00
Faizaan GaganandGitHub 3049f3edda support _rebuild_tensor method interception (#13253) 2025-11-13 09:41:21 -08:00
Harald SchäferGitHubGeorge Hotz
 		3af231904e openpilot compile tests: assert pre-rangify speeds (#12775) 
* assert pre-rangify speeds

* typo

---------

Co-authored-by: George Hotz <[email protected]>
 2025-11-13 09:39:06 -08:00
George HotzandGitHub faf68c03a8 more mi350x matmul work (#13138) 
* more mi350x matmul work

* broken compute
 2025-11-13 09:09:28 -08:00
Ayman JabrGitHubGeorge Hotz
 		256f81bb02 Fix tracemeta 0 (#13049) 
* chore: tclesius branch resolved

* fix: indentation

---------

Co-authored-by: George Hotz <[email protected]>
 2025-11-13 09:07:11 -08:00
alpharushandGitHub 7e0aaadecd feat: add repro command to summary (#10930) 2025-11-13 08:52:27 -08:00
nimlgenandGitHub 6be86dde17 nv: add timeout when repsonding to rpc (#13260) 2025-11-14 00:42:21 +08:00
nimlgenandGitHub f9b7586e08 roc: fix blob gc (#13256) 2025-11-13 23:38:35 +08:00
George HotzandGitHub 263b724143 one cache and bump it (#13258) 2025-11-13 07:33:31 -08:00
George HotzandGitHub 5efa727b83 move _pool to MovementMixins (#13257) 2025-11-13 07:28:52 -08:00
geohot bcdfc109b5 hotfix: disable flaky test 2025-11-13 06:19:28 -08:00
qazalandGitHub 006dea4c3e roc: only save instruction execs (#13254) 2025-11-13 21:28:40 +08:00
nimlgenandGitHub f9586b38ba system: pci mask and val (#13251) 2025-11-13 20:44:58 +08:00
George HotzandGitHub 7316da3253 new readme (#13250) 
* new readme

* update
 2025-11-13 00:48:28 -08:00
geohot 17aa3379e9 hotfix: improve self_tokenize 2025-11-13 00:18:57 -08:00