sirhcm/tinygrad
1
0
Fork 0
forked from tinygrad/tinygrad
Code Pull Requests 2 Actions Activity
11,453 Commits 336 Branches 15 Tags
remove_programspec
Commit Graph
11453 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
b1tgandGitHub bb307b9e81 fix fp8 vectorization (#12977) 
* fix fp8 vectorization

* add fp8 tc to benchmark
 2025-10-28 13:55:30 -04:00
nimlgenandGitHub c11dd56956 amd: cleanup import urls (#12976) 2025-10-29 00:43:02 +08:00
George HotzandGitHub 5e01cc299b zero len ranges fail (#12974) 
* zero len ranges fail

* fix Python backend

* fix llvm

* fix ptx

* yolo fix nir

* this works...

* always store...

* always store...

* Revert "always store..."

This reverts commit 0816cf344d.
 2025-10-28 22:49:55 +08:00
George HotzandGitHub e936aa7974 cleanups from if range branch (#12973) 2025-10-28 20:58:47 +08:00
qazalandGitHub 901d27b3ba viz: optional text dims try 2 (#12971) 2025-10-28 18:54:28 +08:00
geohot f5a3b33d33 add fun with nhwc convs 2025-10-28 17:12:22 +08:00
George HotzandGitHub 907499b02c clean up GROUP/SINK (#12969) 
* clean up GROUP/SINK

* fix end

* range_str color
 2025-10-28 16:08:10 +08:00
Sieds LyklesandGitHub e22c5e7e73 process_replay uses opts argument for KernelInfo.opts_to_apply (#12946) 
* opts_to_apply is opts

* skip beamed kernels

* simpler change

* fix the tensor cores tests for process replay

* use opts
 2025-10-28 09:00:28 +01:00
George HotzandGitHub 6c9560a846 more syntactic sugar for pyrender (#12968) 2025-10-28 15:24:33 +08:00
George HotzandGitHub b0da173f2f add unique to const, fix longstanding bug (#12965) 
* add unique to const, fix longstanding bug

* _force_unique=True

* fix tests

* fix more tests
 2025-10-28 15:11:37 +08:00
Sieds LyklesandGitHub e110f4632a split cat (on cpu) (#12864) 
* split ranges but only on cpu

* except KernelOptError for threads

* use GROUP and END

* no more flatten_range needed

* remove noop end

* always process replay for openpilot

* update test

* skip test

* fix in outs calculation

With the new linearizer the toposort is a problem, this matches the spec
now

* undo that
 2025-10-28 07:55:19 +01:00
qazalandGitHub 3b82dee625 viz: match DEBUG=2 for exec item metadata (#12966) 
* viz: match DEBUG=2 for exec item metadata

* remove repr from kernel
 2025-10-28 14:53:57 +08:00
qazalandGitHub 99589dea81 move viz edge tagging to UOp graph (#12964) 2025-10-28 12:46:23 +08:00
George HotzandGitHub bbe0bebbf3 no range tags in kernels (#12962) 2025-10-28 12:33:48 +08:00
George HotzandGitHub 39c2117dea cleanup pyrender (#12961) 2025-10-28 10:47:39 +08:00
George HotzandGitHub 2832954bcb test with IGNORE_OOB=0 (#12960) 2025-10-28 10:32:19 +08:00
George HotzandGitHub 7784cec48e pytest-split on spec (#12959) 2025-10-28 10:09:01 +08:00
George HotzandGitHub 4d817a289e simplify spec (#12958) 
* simplify spec

* more
 2025-10-28 09:52:32 +08:00
George HotzandGitHub 62e62d8760 move verify to spec / cleanup (#12956) 
* move verify to spec / cleanup

* lil

* more explicit
 2025-10-28 08:58:10 +08:00
wozeparrotandGitHub 24884c6768 fix: don't use KITTENS_HOPPER for 4090 (#12954) 2025-10-27 17:19:53 -07:00
nimlgenandGitHub 372d9e5753 hcq: helper for visible devices (#12950) 
* hcq: helper for visible devices

* fix

* f
 2025-10-28 02:27:56 +08:00
Justin ErenkrantzandGitHub f2ffe9c8cf Apply an override for nbio 7.3.0 to 7.2.0. (#12949) 2025-10-27 11:10:10 -07:00
qazalandGitHub 63484d837e Revert "viz graph drawing cleanups (#12933)" (#12947) 
This reverts commit 189582db5e.
 2025-10-28 00:39:37 +08:00
chenyuandGitHub a79832b01f control_flow.py -> linearizer.py [pr] (#12948) 2025-10-27 12:38:13 -04:00
b1tgGitHubchenyu
 		45e2f916a3 add quantize fp8 in llama3 (#12893) 
* add quantize fp8 in llama3

* don't truncate fp8 alu result

* cast to float32 before matmul

* --model weights/LLaMA-3/8B-SF-DPO/

---------

Co-authored-by: chenyu <[email protected]>
 2025-10-27 10:22:57 -04:00
George HotzandGitHub 25c2da1579 check SPEC=2 in CI (#12945) 
* check SPEC=2 in CI

* split SPEC=2

* fast enough
 2025-10-27 21:53:57 +08:00
Sieds LyklesandGitHub 072f7c35c5 fix in/outs calculation in ProgramSpec (#12937) 
With the new linearizer the toposort is a problem, this matches the spec
now
 2025-10-27 12:31:41 +01:00
qazalandGitHub e93c9bf6a7 viz: extend main code block to full height (#12944) 2025-10-27 18:43:49 +08:00
George HotzandGitHub 273b1f914d new pyrender, tested with SPEC=2 (#12934) 
* pyrender always works with SPEC=3

* test pyrender

* work

* work

* work

* .sintify

* v const

* kernelize

* pyrender

* viz always

* optional forced_reshape

* cleanups
 2025-10-27 18:41:51 +08:00
George HotzandGitHub 701a632907 move VECTORIZE/CONST (#12942) 2025-10-27 17:37:13 +08:00
nimlgenandGitHub 95748a4518 nv: map vram after resets (#12938) 2025-10-27 17:17:07 +08:00
George HotzandGitHub 8fb545c475 don't late simplify on marg (#12941) 2025-10-27 17:07:41 +08:00
George HotzandGitHub 7139e036c5 bugfixes from pyrender (#12940) 2025-10-27 16:56:53 +08:00
George HotzandGitHub 804133cffd rename RECIP to RECIPROCAL (#12939) 2025-10-27 16:53:13 +08:00
nimlgenandGitHub f4da94af28 system: reset is a method of pcidevice (#12936) 2025-10-27 16:21:10 +08:00
wozeparrotandGitHub 6b54378eba working kitten matmul (#12935) 2025-10-26 23:40:49 -07:00
qazalandGitHub 189582db5e viz graph drawing cleanups (#12933) 
* viz: make node label dims optional

* inplace edge updates

* change that
 2025-10-27 13:59:32 +08:00
qazalandGitHub 70ba84eb04 viz: generic node label centering (#12925) 
* viz: correct node label centering

* matches

* overlay

* the other way
 2025-10-27 12:02:34 +08:00
Sieds LyklesandGitHub eaeaea2f9c pyrender Ops.SPECIAL and use correct dtype for Ops.RANGE rendering (#12931) 2025-10-27 03:21:34 +01:00
nimlgenandGitHub 8c1368cab6 system: class PCIBarInfo (#12930) 
* system: class PCIBarInfo

* fix
 2025-10-27 03:57:42 +08:00
nimlgenandGitHub f00009c731 hcq: drivers take pcidev (#12929) 
* hcq: drivers take pcidev

* fix nv
 2025-10-26 20:43:51 +08:00
ttomsaandGitHub 99a519f068 linearizer cleanup (#12923) 
* cleanup

* comments

* also this
 2025-10-26 18:30:12 +08:00
George HotzandGitHub c0c24d3a70 cleanup wmma (#12927) 
* cleanup wmma

* fix test_ops failures on android
 2025-10-26 18:26:47 +08:00
George HotzandGitHub 0a32ab0006 nitpicks from typecheckers (#12926) 
* nitpicks from the typechecker

* more
 2025-10-26 17:52:55 +08:00
geohot db5c918215 source extra/cl_android.sh to fix opencl on android 2025-10-26 15:27:51 +08:00
qazalandGitHub c94e597b3e viz ui selector cleanups (#12924) 2025-10-26 14:40:47 +08:00
chenyuandGitHub 94701d4838 clean up divide_exact order [pr] (#12919) 
do the const first since ADD can also call into that
 2025-10-25 18:47:57 -04:00
chenyuandGitHub e18922f111 limit AND const min max to ints [pr] (#12918) 2025-10-25 16:07:52 -04:00
nimlgenandGitHub 92324172be amd: refactor usb into usbdevice (#12916) 
* amd: refactor usb into usbdevice

* nu

* my bad

* ops

* my bad
 2025-10-26 01:00:19 +08:00
qazalandGitHub 3b192f5eac split viz graph rendering from dag layout (#12914) 2025-10-25 15:36:44 +08:00