nimlgen/tinygrad
1
0
Fork 0
forked from tinygrad/tinygrad
Code Pull Requests Activity
13,588 Commits 334 Branches 15 Tags
b2e95b2db3675a5f0fcee4c3705103f7ef2afe34
Commit Graph
68 Commits
Author SHA1 Message Date
chenyuandGitHub 03943cd1a0 use more _uop for cleanup [PR] (#16531) 
`t.uop if isinstance(t, Tensor) else t` -> `t._uop`
 2026-06-07 17:41:36 -04:00
chenyuandGitHub 8a4203638a make full with buffer=False deviceless (#16483) 
affects arange and eye
 2026-06-03 12:35:59 -04:00
chenyuandGitHub 945ed4f689 revert const unique changes (#16395) 2026-05-27 00:06:41 -04:00
chenyuandGitHub 0b88827482 remove CONST(UNIQUE) (#16383) 2026-05-26 14:45:22 -04:00
chenyuandGitHub cdeb861828 invalids is empty [pr] (#16353) 2026-05-25 16:11:38 -04:00
chenyuandGitHub 5d5e02871f remove Tensor.from_uop (#16344) 
and no device for const in Tensor init
 2026-05-24 18:53:09 -04:00
chenyuandGitHub c1076ed56c Tensor.device and UOp.device can be None (#16255) 2026-05-18 22:08:10 -04:00
chenyuandGitHub 218d6b8988 delete old UOp.size [pr] (#15756) 2026-04-15 23:21:00 -04:00
George HotzandGitHub ae7090b13b print function timing with DEBUG=2 (#15468) 
* add DEBUG=2 function timing

* remove those functions, they aren't useful

* fix spec
 2026-03-25 19:07:32 +08:00
chenyuandGitHub 1abb6297f6 more Tensor(UOp) cleanups (#15364) 
* more Tensor(UOp) cleanups

* function too
 2026-03-19 03:34:30 -04:00
George HotzandGitHub 6e196195d8 add test for flat llama (#15327) 
* add test for flat llama

* simpler

* back to split w1/w3

* env

* still too much ram

* invalid
 2026-03-18 15:16:33 +08:00
George HotzandGitHub 6109117af1 anonymous buffers are Invalid (#15336) 
* anonymous buffers are Invalid

* unique_const

* work

* remove invalid writes

* test_anonymous_buffers_in_function
 2026-03-18 14:52:56 +08:00
George HotzandGitHub 9d95321be3 set allow_implicit=False by default (#15319) 
* set allow_implicit=False by default

* modernize beautiful mnist
 2026-03-17 17:14:38 +08:00
George HotzandGitHub 584ec75aa2 precompile backward (#15311) 
* add precompile backward support

* cleanups

* fix

* compact grad

* split v not split

* simpler

* no NOOPT
 2026-03-17 15:28:40 +08:00
George HotzandGitHub 3ff03be413 call always has tuple (#15297) 
* call always has tuple

* fix pre-commit and simplify

* update

* fix

* move that assert

* tuple

* fix multi

* cleanups

* fix merge
 2026-03-17 10:58:46 +08:00
George HotzandGitHub 476276f4b4 support grads on tuples (#15287) 
* support grads on tuples

* simpler

* grad_fxn works

* cleanups

* unused
 2026-03-16 17:39:34 +08:00
George HotzandGitHub 2e1c81c23f allow_implicit to disable implicit params (#15291) 
* allow_implicit to disable implicit params

* get both Tensor and UOp

* no implicits in llm
 2026-03-16 16:40:14 +08:00
chenyuandGitHub a0d1444790 Tensor.assign is store+after [pr] (#15288) 
* Tensor.assign is store+after [pr]

* put that back
 2026-03-16 04:04:55 -04:00
George HotzandGitHub 08662bc4ab add TUPLE/GETTUPLE, simple tests pass (#15286) 
* simple tuple stuff passes

* resolved
 2026-03-16 15:06:02 +08:00
George HotzandGitHub fb43b415f9 fix symbolic shape call + chunked prefill (#15149) 
* fix precompile for symbolic shape

* chunked prefill

* cleaner

* test that
 2026-03-05 14:02:26 +08:00
George HotzandGitHub 01ddb4c267 add precompile to call (#15099) 
* add precompile to call

* put get back

* something

* after structure

* alt

* keep it call

* resolve call

* resolve linear call

* precompile works with llm

* revert rangeify

* color for debugging

* getenv PRECOMPILE

* clean up deco pattern

* fully recursive sink scheduling

* revert llama

* fix SPEC=2
 2026-03-03 22:32:42 +08:00
George HotzandGitHub fe3ee8c27e fix symbolic shapes in calls (#15021) 
* fix symbolic shapes in calls

* fix after in the big graph

* real tests
 2026-02-26 17:17:18 +08:00
George HotzandGitHub 2655655a0c call gradient creates a call (#15020) 
* function creates a full subgraph

* tests

* fix var

* fix tests

* implict assign/contig

* move kv init
 2026-02-26 14:15:29 +08:00
George HotzandGitHub 0d35b67f2c revert realize to only be buffers (#15008) 
* revert realize to only be buffers

* fix that

* broken attention

* Revert "broken attention"

This reverts commit a23c3cd96c.

* and that
 2026-02-25 22:43:06 +08:00
George HotzandGitHub 68831cd852 add more tests to test_function (#15003) 
* add more tests to test_function

* add function to llm

* function decorator on llm

* works

* symbolic fixups

* minimum change

* implicit inputs

* don't actually update llama yet
 2026-02-25 18:42:06 +08:00
George HotzandGitHub e3fa9896b7 start function and add walk rewrite (#14992) 
* start function and add walk rewrite

* work

* add function on feed_forward

* llm progress

* stuff

* none of that
 2026-02-25 13:56:27 +08:00
George HotzandGitHub a6e496b195 remove Function class [pr] (#8753) 
* remove Function class [pr]

* actually remove function

* fix docs
 2025-01-26 18:58:02 +09:00
George HotzandGitHub 1b4618e257 gradient cleanup (#8750) 
* switch backward to use gradient [pr]

* set device correctly, dedup

* why does that fail?

* add noop cast

* simple backward

* fix beautiful_mnist

* touchups

* set in compute_gradient

* uop_count

* uop_count was wrong

* collections

* no note

* skip that test

* update sched kernel counts

* train mnist is 65

* fix metadata and gc

* fixes

* materialize_grads

* no pathlib stuff

* add contiguous_backward, fix bugs

* add some realize

* fix multi

* remove unused backward passes [pr]

* lower line count
 2025-01-26 09:30:55 +09:00
George HotzandGitHub cb0978b377 add Ops.CONTIGUOUS_BACKWARD (#8743) 2025-01-25 07:28:43 +09:00
chenyuandGitHub f3fdec940d Tensor.mod (#8458) 
it's a python style mod. possibily can be cleaner with a floor div

relaxed the vmin for MOD slightly for cstyle negatives mod, it's more correct and might fix other bugs
 2024-12-31 11:31:42 -05:00
George HotzandGitHub 82833f1b3c a little more typing [pr] (#8346) 
* a little more typing [pr]

* few more
 2024-12-19 22:09:52 -08:00
George HotzandGitHub 9c77e9f9b7 replace Tuple with tuple [pr] (#8344) 
* replace Tuple with tuple [pr]

* replace List with list [pr]

* replace Dict with dict [pr]

* replace Set with set [pr]
 2024-12-19 21:27:56 -08:00
chenyuandGitHub b4bb8de7f4 remove Sigmoid from function.py [pr] (#8318) 2024-12-18 13:23:38 -05:00
George HotzandGitHub 8a50868264 touchup function.py [pr] (#8220) 
* touchup function.py [pr]

* remove ALLOWED_READ_IMAGE

* eh, keep it, just change it
 2024-12-13 13:07:00 -08:00
George HotzandGitHub 8a04a3a77a rename LazyBuffer -> UOp [pr] (#8169) 
* rename LazyBuffer -> UOp [pr]

* fix docs
 2024-12-11 16:15:52 -08:00
chenyuandGitHub 39e0fc05f5 update function to not use gt/lt [pr] (#8025) 
pr does not test this, but it's the same
 2024-12-03 22:39:06 -05:00
qazalandGitHub e84d089ef1 delete ReduceOps, only use REDUCE_AXIS (#7667) 2024-11-13 19:04:27 +08:00
George HotzandGitHub 0c19b6298b rename ops to have unique names (#7522) 2024-11-04 17:09:45 +08:00
George HotzandGitHub b647fa7514 rename MathTraits to maximum [pr] (#7356) 2024-10-29 16:43:04 +08:00
George HotzandGitHub 3989bd2682 idiv + reciprocal [pr] (#7354) 
* idiv + reciprocal

* remove upcast from div

* fix docs
 2024-10-29 15:54:19 +08:00
chenyuandGitHub 13575f080a remove bitcast backward in function.py (#7031) 
bitcast cannot backward
 2024-10-13 10:08:27 -04:00
chenyuandGitHub 23faeacb23 remove outdated comments (#7018) 2024-10-12 10:51:07 -04:00
George HotzandGitHub a71bb09ec3 remove symbolic file [pr] (#7012) 2024-10-12 18:44:44 +08:00
George HotzandGitHub f7f94cd62f bitcast cleanup [pr] (#6933) 2024-10-07 19:16:16 +08:00
George HotzandGitHub 4df5c7a4ef move lazy to engine [pr] (#6886) 
* move lazy to engine [pr]

* engine.lazy
 2024-10-04 23:19:26 +08:00
George HotzandGitHub 4b6732c4f6 safe changes for new symbolic [pr] (#6864) 2024-10-03 20:39:15 +08:00
George HotzandGitHub a28ed7ba4d math trait [run_process_replay] (#6364) 
* math trait [run_process_replay]

* const -> const_like

* Revert "const -> const_like"

This reverts commit 85727c83d3.

* add MathTrait to LazyBuffer

* clean up function

* fixup the rest of function

* fix custom function

* mlb math trait

* fix that test
 2024-09-05 16:19:17 +08:00
chenyuandGitHub 590c0922b6 Tensor.prod (#6250) 
* Tensor.prod

a new reduce op!

* onnx ReduceProd
 2024-08-23 10:06:32 -04:00
chenyuandGitHub 4d1b5781b5 remove UnaryOps.NEG from function.py (#6187) 
* remove function.Neg

prep to remove UnaryOps.NEG

* replace all NEG in function.py
 2024-08-19 17:39:15 -04:00
chenyuandGitHub 96d502d8b7 update function.Max backward (#6190) 
instead of `(1-(x!=max))`, use `(x!=max)!=True`.

prep to remove Unary.NEG, also this can be instruction fused later more easily
 2024-08-19 16:06:14 -04:00