Patrick Tsai 0147174ad6 Embedding in one kernel (#4036) ...

* Embedding is in one kernel

* embedding is one kernel

* rm extra line

* newline

* bert test counts state vars?

* add a test?

* move items around

---------

Co-authored-by: Patrick Tsai <patosai@users.noreply.github.com>

2024-04-02 11:38:21 -04:00

..

codegen

move exec_alu from uops to ops (#4033)

2024-04-01 17:20:53 -07:00

engine

CommandQueue is the future (#3950)

2024-04-01 17:35:48 -07:00

features

don't call contiguous for unpadded const into multi tensor (#4032)

2024-04-01 19:22:14 -04:00

nn

Embedding in one kernel (#4036)

2024-04-02 11:38:21 -04:00

renderer

Move transformations to PatternMatcher + clean up existing patterns (#3997)

2024-03-29 19:42:39 -07:00

runtime

multigpu works (#4040)

2024-04-02 08:29:37 -07:00

shape

fix View.pad arg type (#3845)

2024-03-20 19:36:02 -04:00

__init__.py

move GlobalCounter to helpers (#4002)

2024-03-30 00:30:30 -04:00

buffer.py

move GlobalCounter to helpers (#4002)

2024-03-30 00:30:30 -04:00

device.py

use clang as default instead of llvm for cpu (#4035)

2024-04-02 00:02:18 -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

use *0+1 for Tensor.pow base case, remove function.Zero (#4023)

2024-03-31 19:20:44 -04:00

helpers.py

move GlobalCounter to helpers (#4002)

2024-03-30 00:30:30 -04:00

lazy.py

CommandQueue is the future (#3950)

2024-04-01 17:35:48 -07:00

ops.py

CommandQueue is the future (#3950)

2024-04-01 17:35:48 -07:00

tensor.py

fix Tensor.pow folding for exponent 0 and 1 (#4025)

2024-03-31 19:57:23 -04:00