Yuqi Zhang d0bc2f810b

[Bugfix] Add half type support in reshape_and_cache_cpu_impl on x86 cpu platform (#18430) ...

Signed-off-by: Yuqi Zhang <yuqizhang@google.com>
Co-authored-by: Yuqi Zhang <yuqizhang@google.com>

2025-05-23 01:41:37 -07:00

..

activation.cpp

…

attention.cpp

…

cache.cpp

…

cpu_types_arm.hpp

…

cpu_types_vsx.hpp

[Hardware][Power] Enable compressed tensor W8A8 INT8 quantization for POWER (#17153)

2025-05-07 22:35:03 -07:00

cpu_types_vxe.hpp

…

cpu_types_x86.hpp

[Bugfix] Add half type support in reshape_and_cache_cpu_impl on x86 cpu platform (#18430)

2025-05-23 01:41:37 -07:00

cpu_types.hpp

…

dnnl_helper.hpp

…

layernorm.cpp

…

mla_decode.cpp

…

pos_encoding.cpp

Make key optional for rotary embedding (#17566)

2025-05-07 00:11:46 -07:00

quant.cpp

[Hardware][Power] Enable compressed tensor W8A8 INT8 quantization for POWER (#17153)

2025-05-07 22:35:03 -07:00

shm.cpp

…

torch_bindings.cpp

[Hardware][Power] Enable compressed tensor W8A8 INT8 quantization for POWER (#17153)

2025-05-07 22:35:03 -07:00

utils.cpp

…