Francis LamandGitHub 7c8401fc65 search: skip timing the unoptimized kernel (#4395) ...

* search: skip timing the unoptimized kernel

also ensure the return the unoptimized kernel if no opts are valid
and refactor debugging to a single BEAM_DEBUG variable

* stop early on fast kernels that can't improve enough

2024-05-02 16:48:49 -04:00

..

codegen

search: fix edge cases on screening potential ops (#4394)

2024-05-02 14:53:05 -04:00

engine

simpler reduceop children chasing (#4350)

2024-05-02 15:15:30 +03:00

features

search: skip timing the unoptimized kernel (#4395)

2024-05-02 16:48:49 -04:00

nn

update docs (#4356)

2024-04-30 16:51:42 +09:00

renderer

fix define global (#4383)

2024-05-01 22:32:56 -04:00

runtime

fix define global (#4383)

2024-05-01 22:32:56 -04:00

shape

add consecutive property to shapetracker

2024-05-02 10:41:28 -07:00

__init__.py

add mnist tutorial

2024-04-25 16:08:32 +08:00

buffer.py

new memory scheduler with explicit refcounts (#4198)

2024-04-17 08:46:47 +04:00

device.py

fix define global (#4383)

2024-05-01 22:32:56 -04:00

dtype.py

rename Scalar to ConstType and cast_scalar to as_const (#3946)

2024-03-26 22:39:58 -04:00

function.py

remove downcast_half in sum (#4376)

2024-05-01 11:46:44 -04:00

helpers.py

search: add additional 7 factors to the action space (#4256)

2024-04-22 19:14:23 -04:00

lazy.py

remove downcast_half in sum (#4376)

2024-05-01 11:46:44 -04:00

ops.py

tensor variable (#4362)

2024-04-30 14:08:57 -07:00

tensor.py

fix mean underflow for half tensor (#4377)

2024-05-01 13:38:57 -04:00