github/tinygrad
1
1
Fork 0
mirror of https://github.com/tinygrad/tinygrad.git synced 2026-01-24 22:38:16 -05:00
Code Issues Packages Projects Releases Wiki Activity
4,946 Commits 205 Branches 14 Tags
fc03fc025e14c404c8bc5dc8ded53ba2899d5896
Commit Graph

4946 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
chenyu
fc03fc025e enable sin on METAL in test_dtype_alu (#5298) 2024-07-05 14:52:09 -04:00
qazal
b369e75ed0 refactor schedule creation (#5297) 2024-07-05 21:14:38 +03:00
qazal
5292d37db6 LoadOps.VIEW in the scheduler spec (#5296) 
* refactor to allow_buffer_view

* tests

* fix multi
 2024-07-05 19:43:50 +03:00
hikettei
1ab7a4cff0 Handling Multiple UnaryOps.BITCAST in Function for Proper Kernel Fusion [run_process_replay] (#5172) 
* [Patch] added an option not to ignore view replacing when doing bitcast

* added the testcase

* [Add] reproduced bitcast cannot be fused into a single kernel in the unittest

---------

Co-authored-by: qazal <77887910+Qazalin@users.noreply.github.com>
 2024-07-05 19:16:44 +03:00
chenyu
43c3f73fbc handcode_bert_opt.py (#5295) 
similar to handcode_resnet50_opt.py, one file to check bert kernels without dataset.
 2024-07-05 11:01:20 -04:00
nimlgen
d7835a705c hotfix: fix metal with vars (#5294) 
* hotfix: fix metal with vars

* one more place
 2024-07-05 16:53:40 +03:00
nimlgen
8a548b0b6e metal support offset (#5293) 2024-07-05 16:13:05 +03:00
qazal
1cefbb33ab uop graph tests + type_verify cleanup (#5292) 
* test_cast_alu_fold

* test_double_cast_fold + these should assert
 2024-07-05 13:00:01 +03:00
qazal
341c4a29d1 hotfix: use dtype.scalar() for rendering cast [run_process_replay] [no_assert] (#5290) 2024-07-05 11:29:35 +03:00
chenyu
87d27c45ec minor _broadcast cleanup (#5286) 
`any(x==0 for x in y)` is `0 in y`.

also `get_args(ConstType)` instead of hard coded `float, int, bool`
 2024-07-04 14:25:24 -04:00
SnakeOnex
8c03816ae9 fix README example (#5284) 
* fixed README example

* README test

* changed py -> python markdown code flags in REAME
 2024-07-04 11:15:07 -04:00
nimlgen
2778b6046c new memory scheduler (#5278) 
* new memory schedule algo

* works

* fix

* fix

* linter

* tiny fixes

* do not optimize copy buffers

* mpre comments

* tiny cleanups
 2024-07-04 18:06:04 +03:00
nimlgen
84b3e3bb6f hcq exec no embedded signal (#5142) 2024-07-04 13:29:21 +03:00
Tobias Fischer
0c3a35e5c2 Stable Diffusion v2 Inference (#5283) 
* model implementation

* clip fix, more qol options
 2024-07-03 22:47:10 -04:00
chenyu
e5ba385f03 remove first contiguous in multi from_sharded (#5121) 
second contiguous guarantees lbs are contiguous going into MultiLazyBuffer, don't need the first contiguous
 2024-07-03 19:42:56 -04:00
chenyu
f1ff65e763 remove "no-nans-fp-math"="true" for LLVM (#5282) 
fixed isnan for llvm (still have issue with < nan)
 2024-07-03 17:52:50 -04:00
chenyu
3929a9dc94 fix UOp.cmp_tuple for ALU (#5280) 
* fix UOp.cmp_tuple for ALU

for ALU, use self.arg instead of self.op to compare

* skip that?
 2024-07-03 14:59:05 -04:00
qazal
a9d6a6c339 verify_lazyop with multi reduce (#5276) 
* outsource the assert to the implicit movement op check

* tests
 2024-07-03 20:15:42 +03:00
George Hotz
16e3b8b013 uops work from lowerer [run_process_replay] (#5279) 2024-07-03 09:40:00 -07:00
chenyu
622b7bd556 simpler TinyJit inside TinyJit detection (#5219) 
* simpler TinyJit inside TinyJit detection

suggested in 73395b998b (commitcomment-143660402)

* cannot repro...

* clear the way out

* finally clear
 2024-07-03 12:28:53 -04:00
gip
04ef0fd328 fix: message when applegpu tools missiong (#5236) 2024-07-03 09:07:09 -07:00
reddyn12
d3e244d8b7 prev speed improvements (#5252) 
Co-authored-by: reddyn <nikidsniper@gmail.com>
 2024-07-03 09:06:01 -07:00
nimlgen
21d41f06a2 nv follows HCQCompatAllocRes protocol (#5275) 
* nv follows HCQCompatAllocRes protocol

* fix amd
 2024-07-03 11:34:10 +03:00
Vyacheslav Pachkov
d3e4e21759 add return type for HCQCompatAllocator _alloc (#5267) 
Co-authored-by: nimlgen <138685161+nimlgen@users.noreply.github.com>
 2024-07-03 10:25:44 +03:00
chenyu
191463a919 add timing to SDXL (#5273) 2024-07-02 23:29:54 -04:00
chenyu
b2c3a28a5e nn.RMSNorm (#5272) 
the norm itself has no significant value to add to Tensor method, but we would want Tensor.normalize
 2024-07-02 21:39:01 -04:00
chenyu
9a2a82a77f test stable diffusion unet in ci (#5268) 
unet is parameterized now so can test a smaller one is ci
 2024-07-02 21:37:52 -04:00
chenyu
ce52b10f6f add a flag DISABLE_LOOP_COLLAPSE (#5270) 
workaround if user encountered UNMUL error
 2024-07-02 20:01:11 -04:00
George Hotz
e53b164e1a small changes from lowerer (#5266) 2024-07-02 15:03:54 -07:00
nimlgen
7be776f9af add _alloc_signal/_free_signal to hcq (#5264) 
* add _alloc_signal/_free_signal api

* oops, revert this

* linter
 2024-07-02 23:35:39 +03:00
Tobias Fischer
9a25ee0b9a pixed unet call params (#5262) 2024-07-02 12:40:27 -04:00
qazal
59bc837ad1 refactor gated load rendering [run_process_replay] (#5259) 
* refactor gated load rendering [run_process_replay]

* hotfix: extra line

* remove llvm diff
 2024-07-02 15:13:10 +03:00
nimlgen
e050603b4b nv close fds after mapping (#5246) 2024-07-02 13:57:46 +03:00
qazal
d3cfb6c2e3 refactor UOps.LOAD barrier [run_process_replay] (#5258) 2024-07-02 13:48:47 +03:00
qazal
a1044e6063 iterate over scoped uops once [run_process_replay] (#5255) 2024-07-02 09:21:09 +03:00
wozeparrot
dfbee4f0f5 feat: add blobfile to testing (#5254) 2024-07-01 19:33:58 -07:00
Tobias Fischer
8c9c1cf62f Pulled CLIP and UNet into Seperate Files (#5253) 
* pulled clip and unet into seperate files

* reference cleanup, lru cache fix

* better pool indexing
 2024-07-01 22:33:01 -04:00
chenyu
5808c37302 hotfix disable flaky llama3 beam benchmark on green (#5249) 2024-07-01 15:00:47 -04:00
chenyu
b9122ecdaf revert stable diffusion validation with threefry (#5248) 
* Revert "use threefry in stable diffusion benchmark (#4988)"

This reverts commit 44dfa37c70.

* sdxl and validation fix

* relax threshold
 2024-07-01 14:43:47 -04:00
nimlgen
57e89645cd hcq spec test (#5226) 
* start hcq spec test

* more test

* fixes

* run on amd as well

* test amdgpu exec

* fix amd

* amd mockgpu support sdma timestamp
 2024-07-01 17:36:37 +03:00
Carson Powers
d7839fdc5f Add x!=0 -> (bool)x pattern [run_process_replay] [no_assert] (#5237) 
* x!=0 -> (bool)x pattern

* bool != bool pattern

* redundant upat
 2024-06-30 17:48:45 -07:00
George Hotz
14980f79dd hotfix: unbreak llama 2024-06-30 15:27:54 -07:00
George Hotz
146eb3a811 hotfix: add repeat_interleave docs 2024-06-30 15:25:18 -07:00
George Hotz
3df47bc21e OpenELM + repeat_interleave (#5234) 
* start writing openelm

* progress...hit bug

* repeat_interleave support

* gqa

* add rotary embedding

* spp

* i think it runs correctly

* broken

* output is good now

* cleanups

* no io_uring on android
 2024-06-30 15:18:39 -07:00
nimlgen
7b7b751513 simple hip backend for debugging (#5201) 
* hip backend

* fix mypy

* shorter

* fixes

* tiny changes
 2024-06-30 23:00:11 +03:00
chenyu
88763eb9ff fix stable_diffusion with fp16 (#5239) 2024-06-30 12:59:31 -04:00
chenyu
649641a2f2 fix tqdm with generator without __len__ (#5238) 
it should be treated as total = 0 (just show iteration count).
also removed duplicated ": " in fetch and fixed unit scale with total = 0
 2024-06-30 12:20:59 -04:00
chenyu
fd53b6d901 tqdm supports fractional blocks (#5233) 
enabled progress bar match in test, it matched perfectly now
 2024-06-29 22:30:18 -04:00
chenyu
ae10ae4722 simplify tqdm scale math (#5231) 
expand the log of log stuff
 2024-06-29 21:17:40 -04:00
hikettei
ad1ca7da64 [Feature] Added BinaryOps.AND/BinaryOps.OR (#5223) 
* [Feature] Added BinaryOps.AND/BinaryOps.OR

* Add: __rand__, __ror__
 2024-06-29 17:20:25 -07:00