tinygrad/tinygrad
Ahmed Harmouche fb4d830a2a
Fix cast error in render_load in wgsl (#1956)
* Fix cast error in wgsl

* User render_cast intead of introducing new method

* Make it shorter

* Add back webgpu tests: efficientnet and dtypes
2023-10-04 02:29:14 -07:00
..
codegen Revert "optimizer: add matvec optimizations (#1753)" (#1959) 2023-10-03 00:28:42 -07:00
nn Refactor Conv2d/ConvTranspose2d into a single parent class (#1906) 2023-09-24 14:23:41 +08:00
renderer Fix cast error in render_load in wgsl (#1956) 2023-10-04 02:29:14 -07:00
runtime move to realize.py (#1961) 2023-10-03 07:25:40 -07:00
shape perf: assert behind if is not optimized (#1847) 2023-09-29 11:07:24 -07:00
graph.py more lazy cleanup (#1938) 2023-09-29 00:53:29 -07:00
helpers.py Do not import typing_extensions at runtime (#1927) 2023-09-28 01:57:28 -07:00
jit.py fix jitted dist (#1955) 2023-10-02 11:45:13 -04:00
lazy.py unrealized consts everywhere (#1963) 2023-10-04 01:48:10 -07:00
mlops.py reorder a few things (#1915) 2023-09-25 10:17:21 +08:00
ops.py unrealized consts everywhere (#1963) 2023-10-04 01:48:10 -07:00
realize.py unrealized consts everywhere (#1963) 2023-10-04 01:48:10 -07:00
tensor.py simplify line (#1950) 2023-10-02 03:19:15 -07:00