mirror of
https://github.com/tinygrad/tinygrad.git
synced 2026-06-24 02:14:17 +00:00
* revert the .detach() in layernorm it's only correct in LayerNorm where input is the data, and not correct in GroupNorm and InstanceNorm that reused layernorm. Added backward tests for weights, bias and input for these norms. * bigger atol for llvm * relax backward more |
||
|---|---|---|
| .. | ||
| codegen | ||
| engine | ||
| nn | ||
| renderer | ||
| runtime | ||
| shape | ||
| __init__.py | ||
| device.py | ||
| dtype.py | ||
| function.py | ||
| helpers.py | ||
| lazy.py | ||
| multi.py | ||
| ops.py | ||
| tensor.py | ||