tinygrad/tinygrad
2
0
Fork 3
mirror of https://github.com/tinygrad/tinygrad.git synced 2026-08-29 14:16:06 +00:00
Code Issues Packages Projects Releases Wiki Activity
10,908 Commits 340 Branches 16 Tags
1c9f7206547af7b9e8d67f0014d7e4696e2f0698
Commit Graph
10908 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
chenyuandGitHub 1c9f720654 remove unused type ignore [pr] (#13095) 2025-11-04 10:08:07 -05:00
nimlgenandGitHub c857dc5af0 autogen: try/except in try_dlopen (#13094) 
* autogen: try/except in try_dlopen

* ugh
 2025-11-04 22:51:53 +08:00
nimlgenandGitHub eaf7cbc178 amd: flush sqtt after each kernel (#13092) 
* amd: flush sqtt after each kernel

* merge for rgp
 2025-11-04 22:12:48 +08:00
qazalandGitHub 96417665e8 show sqtt decoder errs in viz (#13088) 
* show sqtt decoder errs in viz

* don't touch roc.py

* give hljs a default language

* work from tinyr9

* work
 2025-11-04 22:05:06 +08:00
nimlgenandGitHub 49191ada77 roc: install sqtt decoder (#13091) 
* roc: install?

* msg

* 0.1.4
 2025-11-04 18:56:01 +08:00
nimlgenandGitHub 16f1f644ba amd: remove sqtt=2 (#13090) 2025-11-04 18:29:24 +08:00
nimlgenandGitHub 2e97eaa866 roc: no nullptr when no wave instructions (#13087) 2025-11-04 17:32:14 +08:00
wozeparrotandGitHub 9c00c0688a tk fa: use 16x64 tiles (#13086) 2025-11-03 18:25:38 -08:00
wozeparrotandGitHub 4ed0f216b5 fix: make max_matmul run again (#13085) 2025-11-03 18:09:09 -08:00
chenyuandGitHub ca17718b6d remove symbolic_flat (#13083) 
* remove symbolic_flat

some kernels are different but sometimes it's better so not clear, will merge as long as benchmark passes

* test_location
 2025-11-03 17:25:21 -05:00
chenyuandGitHub fda720e013 simpler _is_balanced [pr] (#13082) 
returns False earlier
 2025-11-03 16:47:14 -05:00
chenyuandGitHub ddf01fdb15 revert mlperf.yml setting (#13080) 2025-11-03 15:24:13 -05:00
qazalandGitHub 6df34a5887 lint sqtt parser with mypy (#13079) 
* llvm address table errs

* mypy likes annotated dicts

* unwrap nullable
 2025-11-04 00:53:59 +08:00
qazalandGitHub 2d2040bc92 viz: tabulate sqtt (#13078) 
* viz: tabulate sqtt

* nomore asdict
 2025-11-04 00:03:15 +08:00
nimlgenandGitHub dfde3f54d9 rocprof: use llvm disasm (#13077) 
* rocprof: use llvm disasm

* rm
 2025-11-03 23:58:58 +08:00
qazalandGitHub 27d42fd575 sqtt decoder print behind DEBUG>=5 (#13076) 
* sqtt decoder print behind DEBUG>=5

* gfx version stuff also behind 5
 2025-11-03 23:20:03 +08:00
George HotzandGitHub 416b15cc59 improve uop matmul syntax (#13074) 
* improve uop matmul syntax

* store takes const

* copy

* cleanups

* faster and simpler

* label them reduce

* better syntax

* touchup
 2025-11-03 21:34:26 +08:00
nimlgenandGitHub 08855c162b amd: correct sqtt_read for several xccs (#13075) 
* amd: correct sqtt_read for several xccs

* default mask
 2025-11-03 19:59:56 +08:00
qazalandGitHub 1c0d4f1cd2 viz: counters loader (#12987) 
* standalone custom loader

* first iteration on the ui

* work

* add center helper

* add edge offsets

* enumerate all edge types

* try dagre layout algorithm

* simpler spec

* bring back double edges

* more work on edge paths

* aesthetics

* custom edges also works

* dimmer inactive links

* cleanup

* cleanup

* split out the ncu layout

* this is just a k/v map now

* rm that

* more cleanup and comments

* do work

* also this work

* simpler start

* rm that

* sqtt work

* view sqtt

* sqtt

* --custom is just in profile

* wrap c call

* from tinygrad install

* eg. module not found
 2025-11-03 19:42:36 +08:00
George HotzandGitHub 1e3d6e49a6 index slicing + allclose (#13071) 
* continue work on slicing+allclose

* Revert "Revert "slicing + allclose""

This reverts commit 6c7a12f21c.

* fix tests + better syntax

* forgot an after

* slot is an integer
 2025-11-03 13:01:48 +08:00
geohot 6c7a12f21c Revert "slicing + allclose" 
This reverts commit c9a1e35b1e.
 2025-11-03 12:05:44 +08:00
geohot c9a1e35b1e slicing + allclose 2025-11-03 12:00:45 +08:00
chenyuandGitHub a317d6e625 extra/amdpci/setup_python_cap.sh (#13070) 2025-11-02 19:19:36 -05:00
chenyuandGitHub ad501ce50a mlperf cron install tqdm (#13069) 
one more...
 2025-11-02 18:09:27 -05:00
chenyuandGitHub 2c8d619147 mlperf cron install influxdb3-python (#13068) 2025-11-02 17:55:40 -05:00
chenyuandGitHub 4c22f089fc mlperf cron install tensorflow try 2 (#13067) 2025-11-02 17:11:01 -05:00
chenyuandGitHub c58cf91850 mlperf cron install tensorflow (#13066) 2025-11-02 16:48:05 -05:00
chenyuandGitHub 74db65cf72 update mlperf bert LOGMLPERF (#13065) 2025-11-02 15:26:37 -05:00
chenyuandGitHub b18293de96 train bert in mlperf cron (#13064) 
more relevant now
 2025-11-02 15:04:02 -05:00
nimlgenandGitHub be0028d3ce amd: universal set_grbm (#13062) 
* amd: universal set_grbm

* fix
 2025-11-03 03:35:55 +08:00
nimlgenandGitHub 37a730abce amd: fix pmc sq gfx11+ (#13058) 
* amd: fix pmc sq gfx11+

* fix
 2025-11-02 21:56:47 +08:00
qazalandGitHub 24054bb655 viz: check overlay width after layout (#13060) 2025-11-02 21:47:58 +08:00
George HotzandGitHub 962d980919 fuse hasn't worked since rangeify, remove it (#13057) 2025-11-02 14:01:52 +08:00
George HotzandGitHub 036ee9f84c Self type + mixins (#13056) 
* use Self type

* mixin

* fix later
 2025-11-02 13:30:01 +08:00
George HotzandGitHub 8cbef912d2 move reshape to MathTraits (#13054) 
* move reshape to MathTraits

* confirm it works in amd_uop_matmul
 2025-11-02 12:56:15 +08:00
George HotzandGitHub 1ff341bae5 python 3.11 is now required (#13055) 2025-11-02 12:55:40 +08:00
geohot 267be7fc5e fp16 acc 2025-11-02 12:53:04 +08:00
wozeparrotandGitHub 8206eab4fc fix: tk fa 4 workers (#13052) 2025-11-01 16:41:29 -07:00
Sieds LyklesandGitHub 885b6dea9e multiple reduce range arange folding (#13047) 
* multi reduce arange folding

* add test

* cvar to var

* add circular_pad_bw test
 2025-11-01 22:11:26 +01:00
Sieds LyklesandGitHub f97fb703c8 catch group error in matvec heuristic (#13051) 2025-11-01 22:09:35 +01:00
Sieds LyklesandGitHub ecb8565f67 Revert "Better cleanup of arange bufferize (#13046)" (#13048) 
This reverts commit c99b7dfd4a.
 2025-11-01 18:09:37 +01:00
Sieds LyklesandGitHub c99b7dfd4a Better cleanup of arange bufferize (#13046) 
* check for reduce and index instead of cast

* add test
 2025-11-01 16:16:31 +01:00
nimlgenandGitHub 051aab5481 open viz with sqtt flags (#13001) 2025-11-01 22:48:17 +08:00
nimlgenandGitHub 2db57f3a97 amd: better msg when out of perf regs (#13042) 2025-11-01 22:47:50 +08:00
chenyuandGitHub bebec73471 write custom_sum with set and after (#13045) 2025-11-01 10:45:30 -04:00
George HotzandGitHub e98506735b add CONTRACT support to UOp programs (#13043) 
* add contract support

* use contract

* 342 tflops
 2025-11-01 19:11:32 +08:00
George HotzandGitHub 65a0a31475 AMD mi350x matmul from stream (#13040) 
* works

* working mfma

* 120 TFLOPS

* regs

* 192 TFLOPS

* try pipelining

* something

* notes

* contract

* linter to 3.11

* that was a bug
 2025-11-01 17:55:19 +08:00
chenyuandGitHub f396df26ea test custom sum (#13039) 
* test custom sum

this is higher level than set and after?

* only float
 2025-10-31 19:25:56 -04:00
nimlgenandGitHub a23226e61e amd: pmc for gfx9 (#13036) 
* amd: pmc for gfx9

* xcc

* vmid mask

* ugh

* tiny

* minor

* sorryg
 2025-11-01 04:26:34 +08:00
nimlgenandGitHub f6786c1bfd autogen: py314 (#13038) 
* autogen: py314

* bump py?
 2025-11-01 04:02:19 +08:00