sirhcm/tinygrad
1
0
Fork 0
forked from tinygrad/tinygrad
Code Pull Requests 1 Actions Activity
14,300 Commits 331 Branches 15 Tags
simple_rangeify
Commit Graph
1412 Commits
Author SHA1 Message Date
George HotzandGitHub 7edf80a48a small changes from new rangeify + remove flaky tc tests (#17486) 
* small changes from new rangeify

* remove test/opt/test_tensor_cores.py
 2026-08-10 15:58:49 -07:00
nimlgenandGitHub e29606f07e hcq2: copy kernel (#17480) 
* hcq2: copy with kernel

* test

* x
 2026-08-10 17:28:46 +03:00
nimlgenandGitHub 8611fe22a7 fix hevc (#17477) 
* hevc tests

* x
 2026-08-10 13:33:49 +03:00
George HotzandGitHub 566f32fe9f move platform tests to platform.yml (#17475) 
* ci: split mac/windows/qcom-cl tests into platform.yml

Move the 6 jobs that don't run on Linux (4 macos, 1 windows, 1 QCOM CL
compile test on arm) out of test.yml into a separate Platform Tests
workflow so they run (and can be gated/runners-matched) independently.

* ci: gate platform tests to the upstream repo

Skip mac/windows/qcom-cl jobs anywhere but tinygrad/tinygrad, so the
Platform Tests workflow is disabled on the gitea fork (and any fork).

* ci: revert repo gate on platform tests

Job-level if is only evaluated by gitea when a runner with matching
labels fetches the task; with no mac/windows/arm runners the jobs queue
forever. Disable the workflow on the instance instead.
 2026-08-09 23:25:18 -07:00
chenyuandGitHub 4a3b8f6501 better _drop_valid_stmts [pr] (#17454) 2026-08-07 15:18:35 -04:00
qazalandGitHub 9636dd1a25 test MXFP4 llama without hipcc (#17435) 
* test MXFP4 llama without hipcc

* first pythonpath then dev
 2026-08-06 17:31:40 +09:00
nimlgenandGitHub 5b0b68ec55 remove debug from test (#17410) 2026-08-05 15:47:40 +03:00
nimlgenandGitHub 874d33128b hcq2 benchmark (#17235) 
* hcq2 in ci?

* fix

* traning

* x

* x

* x

* recover

* debug

* impler

* x

* x

* x

* hcq2: group input scatter plans by destination

* hcq2: simplify input scatter tables

* x
 2026-08-05 10:00:42 +03:00
RaineGitHubGeorge Hotz
 		77e124e455 fix AMD WMMA emulation and test in CI (#17184) 
* fix SPEC=1 test_tensor_cores

* implement i32 WMMA for RDNA3, add regression test to CI

* gfx950 scaled mfma llvmir fix

* detect VOP3PX2 in emu

* start cdna4 scaled mfam emu

* fix gfx12 llvmir signatures

* oops

* fix

* fix src2 const field extraction (gpt)

* scaled mfma fixes cdna4 (kimi)

* fp8 out breaks mfma (glm)

* fix const signature

* another

* fix f string for linter

* lint

* clean

* and a final lint

* .

* fix mypy

* skip slow tests on ci

* reduce unroll tensor shape -> 64x64

---------

Co-authored-by: George Hotz <[email protected]>
 2026-08-04 23:25:32 -07:00
sirhcmandGitHub de57be1f26 kill nvidia pids at benchmarks start (#17406) 2026-08-04 23:45:49 -04:00
chenyuandGitHub a2385ae21d MAX_LINE_COUNT=26000 (#17378) 
oh well
 2026-08-03 15:37:58 -04:00
George HotzandGitHub 099d69ff7d ci: split macos unit test into metal and mock runners (#17346) 2026-07-31 19:41:18 -07:00
sirhcmandGitHub 15d515299e heuristics: try multiple TC axes (#17341) 2026-07-31 19:25:18 -04:00
sirhcmandGitHub b95bd5b2a5 don't reset chestnut in benchmark (#17333) 2026-07-31 12:39:04 -04:00
wozeparrotandGitHub 4f5cadd15d gptoss ci (#17325) 2026-07-31 05:51:58 -07:00
sirhcmandGitHub 13452b3775 benchmark comma big model (#17312) 2026-07-31 01:37:34 -04:00
sirhcmandGitHub b290372121 ftdi reset chestnut before running comma benchmark (#17306) 2026-07-30 14:28:45 -04:00
sirhcmandGitHub da15c43e51 update openpilot benchmarks (#17304) 2026-07-30 14:22:20 -04:00
George HotzandGitHub dd16d5aead apply shrink bugfix for 3.11 (#17271) 2026-07-28 19:03:06 -07:00
chenyuandGitHub 291ee435bb qwen3.6 for 27b and 35b-a3b (#17268) 2026-07-28 21:11:49 -04:00
chenyuandGitHub 23e9e76e8c DEFAULT_FLOAT/DEFAULT_INT ContextVar [pr] (#17265) 2026-07-28 19:08:18 -04:00
chenyuandGitHub fde3a8faff CAPTURE_PROCESS_REPLAY=0 default chaging test [PR] (#17261) 
* CAPTURE_PROCESS_REPLAY=0 default chaging test [PR]

quick patch before making default dtype context vars, which is quite annoying

* few more
 2026-07-28 17:32:35 -04:00
George HotzandGitHub a9ad08064e make the github actions runners generic for gitea (#17254) 2026-07-28 10:48:49 -07:00
qazalandGitHub 19c4d736f2 validate json output of viz.cli in CI (#17232) 
* validate viz.cli --json always prints valid JSON

* highest debug level

* jq empty we don't need a print

* gate that import
 2026-07-27 15:44:24 +09:00
chenyuandGitHub 6a9c23b1c1 more symmetrical div_and_mod_symbolic [pr] (#17145) 2026-07-22 23:34:03 -04:00
chenyuandGitHub 723309b5c0 update hand_coded_optimizations [pr] (#17144) 
only upcast when they share valids
 2026-07-22 22:26:27 -04:00
chenyuandGitHub 8481eba866 allow-unsafe-pr-checkout for szdiff.yml (#17096) 
it uses sz.py on master to parse the change, should be safe
 2026-07-20 15:08:54 -04:00
sirhcmandGitHub 6f1176ea90 benchmarks: test usbgpu copy speeds on comma (#17060) 2026-07-17 02:02:21 -04:00
chenyuandGitHub 0410c9325d make test/null follow the SPEC (#17010) 2026-07-13 14:01:41 -04:00
nimlgenandGitHub e4bdc529c4 hcq2 ci (#17008) 
* hcq2 ci

* x
 2026-07-13 19:29:08 +03:00
sirhcmandGitHub f1ccb85a27 ci: use llvm-20 in amd tests (#16982) 2026-07-11 02:26:10 -04:00
George HotzandGitHub 43ad225d36 nv_610 support (glm) (#16979) 
* nv_610 support

* unbump onnx

* fix autogen workflow
 2026-07-10 20:37:30 -07:00
geohot 2b7c298aaf hotfix: remove SPEC=2 timeout to match other jobs 2026-07-10 09:35:48 -07:00
George HotzandGitHub d8fbbff260 EXPAND adds dims to the front (glm) (#16908) 
* EXPAND adds dims to the front (glm)

* more read images

* simpler + spec

* spec should use n instead of s'

* bump comma to 12
 2026-07-07 11:03:06 -07:00
George HotzandGitHub c92a4c0442 move devectorizer remains into coalese (#16869) 
* move devectorizer remains into coalese

* fix flaky
 2026-07-04 15:36:45 -07:00
qazalandGitHub 07f7383d29 llama: remove unused bf16 assembly gemm (#16859) 
* only hk bf16 gemm

* rm asm gemm

* more cleanup

* half isn't supported in asm gemm anymore

* more test edits

* unused

* remove TestMagicGu

* uop gemm is still tested

* minimal diff
 2026-07-04 18:41:54 +09:00
sirhcmandGitHub 353d8f1e13 use rusticl in ci (#16852) 2026-07-03 23:58:58 -04:00
sirhcmandGitHub e74c7042c3 ci: use tinymesa from pypi (#16835) 2026-07-02 19:25:10 -04:00
sirhcmandGitHub e0d7696ccd split benchmarks (#16812) 2026-07-01 22:28:15 -04:00
sirhcmandGitHub 8472d374ab ci: parallelize fuzz tests (#16805) 2026-06-30 14:14:32 -04:00
sirhcmandGitHub 395eec1866 disable mlperf training benchmark (#16798) 2026-06-29 20:11:16 -04:00
George HotzandGitHub 0bee0e6e39 do full sym in extra symbolic [pr] (#16786) 
* do full sym in extra symbolic [pr]

* put that back to 55
 2026-06-28 08:31:47 -07:00
sirhcmandGitHub f8ddca9a00 qcom: ir3 needs SP_MODE_CNTL.CONSTANT_DEMOTION_ENABLE (#16769) 2026-06-26 19:48:29 -04:00
George HotzandGitHub a94a32ff71 move image to post coalese (#16749) 
* move image to post coalese

* fix types

* dv2

* work

* load_store_indexing

* lsi

* simplify indexing

* always simplify

* more

* whitespace

* no simplify

* no early opt

* fix linter

* exit early without valid

* always simplify

* relax ir3

* no gep

* Revert "no gep"

This reverts commit 3fa4dd6dfa.

* shapes in ctx

* disable IR3
 2026-06-25 23:33:07 -07:00
George HotzandGitHub 5fcb21c1b3 remove vectorize/const symbolic rule [pr] (#16759) 
* remove vectorize/const symbolic rule

* post index symbolic is late

* simpler

* less gates

* that's fine

* this

* work

* don't rerun

* this order

* late removal of index dtype

* skip that test

* it's fine with extra symbolic
 2026-06-25 17:05:14 -07:00
sirhcmandGitHub d5a852b9ee ci: cleanup macos tests (#16760) 2026-06-25 19:47:29 -04:00
sirhcmandGitHub c759301865 ci: cleanup torch backend tests (#16750) 2026-06-25 14:39:36 -04:00
chenyuandGitHub db2257ad09 don't run tinyboxbenchmark on fork (#16741) 2026-06-25 09:12:56 -04:00
sirhcmandGitHub 63f0e08593 start benchmarks cleanup (#16729) 2026-06-24 23:33:46 -04:00
chenyuandGitHub 687ade119e IMAGE hand_coded_optimizations update (#16720) 2026-06-23 21:55:28 -04:00