Fix minor details

Author: orion160

recipes_source/recipes/tuning_guide.py

@@ -213,7 +213,7 @@ def gelu(x):
 
 ###############################################################################
 # Typically, the following environment variables are used to set for CPU affinity with GNU OpenMP implementation. ``OMP_PROC_BIND`` specifies whether threads may be moved between processors. Setting it to CLOSE keeps OpenMP threads close to the primary thread in contiguous place partitions. ``OMP_SCHEDULE`` determines how OpenMP threads are scheduled. ``GOMP_CPU_AFFINITY`` binds threads to specific CPUs.
-# An important tuning parameter is core pinning which prevent the threads of migrating between multiple CPUs, enchancing data location and minimizing intra core communication.
+# An important tuning parameter is core pinning which prevent the threads of migrating between multiple CPUs, enchancing data location and minimizing intra-core communication.
 #
 # .. code-block:: sh
 #
@@ -327,14 +327,13 @@ def gelu(x):
 #
 # Hardware tensor core operations tend to use a different floating point format
 # which sacrifices precision at expense of speed gains.
-
-torch.backends.cuda.matmul.allow_tf32
-
 # Prior to pytorch 1.12 this was enabled by default but since this version
 # it must be explicitly set as it can conflict with some operations which do not
 # benefit from Tensor core computations.
 
 
+torch.backends.cuda.matmul.allow_tf32
+
 ###############################################################################
 # Use CUDA Graphs
 # ~~~~~~~~~~~~~~~~~~~~~~~