Nikhil Gupta 359d293006

[fix]: add Arm 4bit fused moe support (#23809) ...

Signed-off-by: Nikhil Gupta <nikhil.gupta2@arm.com>

2025-09-24 01:32:22 +00:00

..

sgl-kernels

[Doc]: fix typos in various files (#24726)

2025-09-12 06:43:12 -07:00

activation.cpp

[Kernel][CPU] Add Quick gelu to CPU (#5717)

2024-06-21 06:39:40 +00:00

attention.cpp

[CI] change spell checker from codespell to typos (#18711)

2025-06-11 19:57:10 -07:00

cache.cpp

[Kernel][CPU] CPU MLA (#14744)

2025-03-25 09:34:59 +00:00

cpu_types_arm.hpp

[Hardware][CPU] Vllm int8 quantization enablement for ARM CPU (#14129)

2025-07-10 15:59:04 +00:00

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

[Doc]: fix typos in various files (#24726)

2025-09-12 06:43:12 -07:00

cpu_types_x86.hpp

[CPU] Refactor CPU W8A8 scaled_mm (#23071)

2025-08-21 09:34:24 +08:00

cpu_types.hpp

Fix: Add explicit #include <omp.h> for OpenMP compatibility on certain toolchains (#24951)

2025-09-18 17:43:23 +08:00

dnnl_helper.cpp

[CPU] Refactor CPU unquantized linear (#24150)

2025-09-04 14:28:45 +08:00

dnnl_helper.h

[CPU] Refactor CPU unquantized linear (#24150)

2025-09-04 14:28:45 +08:00

dnnl_kernels.cpp

[Bugfix] Fix Stream usage in CPU model runner and OneDNN kernel check (#25046)

2025-09-17 05:54:02 -07:00

layernorm.cpp

[Kernel][Misc] Use TORCH_LIBRARY instead of PYBIND11_MODULE for custom ops (#5047)

2024-06-09 16:23:30 -04:00

mla_decode.cpp

[Kernel][CPU] CPU MLA (#14744)

2025-03-25 09:34:59 +00:00

pos_encoding.cpp

Make key optional for rotary embedding (#17566)

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

shm.cpp

[CPU] Enable shared-memory based pipeline parallel for CPU backend (#21289)

2025-07-21 09:07:08 -07:00

torch_bindings.cpp

[fix]: add Arm 4bit fused moe support (#23809)

2025-09-24 01:32:22 +00:00

utils.cpp

Support no privileged mode on CPU for docker and kubernetes deployments (#19241)

2025-06-11 04:11:47 -07:00