mlx/mlx
Angelos Katharopoulos dfa9f4bc58
An initial quantized matmul implementation (#205)
* Add quantized matvec
* Add quantized matrix matrix with 2nd matrix transposed
* Add quantized matmul tests
* Add a slow cpu quantized matmul
* Add a slightly faster vectorized cpu version
2023-12-18 23:18:57 -08:00
..
3rdparty jagrit's commit files 2023-11-29 10:52:08 -08:00
backend An initial quantized matmul implementation (#205) 2023-12-18 23:18:57 -08:00
types copyright + ack 2023-11-30 11:12:53 -08:00
allocator.cpp copyright + ack 2023-11-30 11:12:53 -08:00
allocator.h copyright + ack 2023-11-30 11:12:53 -08:00
array.cpp copyright + ack 2023-11-30 11:12:53 -08:00
array.h add base kwarg to rope (#186) 2023-12-15 16:47:59 -08:00
CMakeLists.txt angelos's commit files 2023-11-29 10:42:59 -08:00
device.cpp copyright + ack 2023-11-30 11:12:53 -08:00
device.h copyright + ack 2023-11-30 11:12:53 -08:00
dtype.cpp copyright + ack 2023-11-30 11:12:53 -08:00
dtype.h random generation fix (#80) 2023-12-08 10:40:57 -08:00
fft.cpp copyright + ack 2023-11-30 11:12:53 -08:00
fft.h copyright + ack 2023-11-30 11:12:53 -08:00
graph_utils.cpp copyright + ack 2023-11-30 11:12:53 -08:00
graph_utils.h copyright + ack 2023-11-30 11:12:53 -08:00
load.cpp copyright + ack 2023-11-30 11:12:53 -08:00
load.h copyright + ack 2023-11-30 11:12:53 -08:00
mlx.h copyright + ack 2023-11-30 11:12:53 -08:00
ops.cpp An initial quantized matmul implementation (#205) 2023-12-18 23:18:57 -08:00
ops.h An initial quantized matmul implementation (#205) 2023-12-18 23:18:57 -08:00
primitives.cpp An initial quantized matmul implementation (#205) 2023-12-18 23:18:57 -08:00
primitives.h An initial quantized matmul implementation (#205) 2023-12-18 23:18:57 -08:00
random.cpp random generation fix (#80) 2023-12-08 10:40:57 -08:00
random.h copyright + ack 2023-11-30 11:12:53 -08:00
scheduler.cpp copyright + ack 2023-11-30 11:12:53 -08:00
scheduler.h copyright + ack 2023-11-30 11:12:53 -08:00
stream.h copyright + ack 2023-11-30 11:12:53 -08:00
transforms_impl.h format 2023-11-30 11:50:50 -08:00
transforms.cpp copyright + ack 2023-11-30 11:12:53 -08:00
transforms.h copyright + ack 2023-11-30 11:12:53 -08:00
utils.cpp implemented Flatten Module (#149) 2023-12-16 21:54:37 -08:00
utils.h Added mx.stack c++ frontend impl (#123) 2023-12-14 13:21:19 -08:00