Fix test tolerance and patch bump (#1315)

Author: angeloskath

CMakeLists.txt

@@ -24,7 +24,7 @@ option(MLX_METAL_JIT "Use JIT compilation for Metal kernels" OFF)
 option(BUILD_SHARED_LIBS "Build mlx as a shared library" OFF)
 
 if(NOT MLX_VERSION)
-  set(MLX_VERSION 0.16.1)
+  set(MLX_VERSION 0.16.2)
 endif()
 
 # --------------------- Processor tests -------------------------

python/tests/test_fast.py

@@ -357,9 +357,9 @@ def test_layer_norm_grad(self):
 
         gx1, gw1, gb1 = mx.grad(f1, argnums=(0, 1, 2))(x, w, b, y)
         gx2, gw2, gb2 = mx.grad(f2, argnums=(0, 1, 2))(x, w, b, y)
-        self.assertLess(mx.abs(gx1 - gx2).max(), 1e-5)
-        self.assertLess(mx.abs(gw1 - gw2).max() / mx.abs(gw1).mean(), 1e-5)
-        self.assertLess(mx.abs(gb1 - gb2).max() / mx.abs(gb1).mean(), 1e-5)
+        self.assertLess(mx.abs(gx1 - gx2).max(), 5e-5)
+        self.assertLess(mx.abs(gw1 - gw2).max() / mx.abs(gw1).mean(), 5e-5)
+        self.assertLess(mx.abs(gb1 - gb2).max() / mx.abs(gb1).mean(), 5e-5)
 
         def gf(f):
             def inner(x, w, b, y):
@@ -370,8 +370,8 @@ def inner(x, w, b, y):
 
         gx1, gw1, gb1 = mx.grad(gf(f1), argnums=(0, 1, 2))(x, w, b, y)
         gx2, gw2, gb2 = mx.grad(gf(f2), argnums=(0, 1, 2))(x, w, b, y)
-        self.assertLess(mx.abs(gx1 - gx2).max() / mx.abs(gx1).mean(), 1e-5)
-        self.assertLess(mx.abs(gw1 - gw2).max() / mx.abs(gw1).mean(), 1e-5)
+        self.assertLess(mx.abs(gx1 - gx2).max() / mx.abs(gx1).mean(), 5e-5)
+        self.assertLess(mx.abs(gw1 - gw2).max() / mx.abs(gw1).mean(), 5e-5)
         self.assertLess(mx.abs(gb1).max(), 1e-9)
         self.assertLess(mx.abs(gb2).max(), 1e-9)
 

setup.py

@@ -163,7 +163,7 @@ def run(self) -> None:
 
     setup(
         name="mlx",
-        version=get_version("0.16.1"),
+        version=get_version("0.16.2"),
         author="MLX Contributors",
         author_email="[email protected]",
         description="A framework for machine learning on Apple silicon.",