Ma Mingfei 62d7454976 optimize conv3d used in patch embedding (#16040)

2026-03-18 22:17:53 -07:00

..

aarch64

…

mamba

…

model

…

x86_64

…

activation.cpp

…

bmm.cpp

…

CMakeLists.txt

…

common.h

…

conv3d.cpp

optimize conv3d used in patch embedding (#16040)

2026-03-18 22:17:53 -07:00

decode.cpp

…

extend.cpp

…

flash_attn.cpp

…

flash_attn.h

…

gemm_fp8.cpp

…

gemm_int4.cpp

[CPU][INT4] Add INT4 kernels for CPU (#8226)

2026-01-29 22:30:13 -08:00

gemm_int8.cpp

…

gemm.cpp

…

gemm.h

[CPU][INT4] Add INT4 kernels for CPU (#8226)

2026-01-29 22:30:13 -08:00

interface.cpp

…

moe_fp8.cpp

…

moe_int4.cpp

[CPU][INT4] Add INT4 kernels for CPU (#8226)

2026-01-29 22:30:13 -08:00

moe_int8.cpp

…

moe.cpp

[CPU][INT4] Add INT4 kernels for CPU (#8226)

2026-01-29 22:30:13 -08:00

norm.cpp

[CPU] support LayerNorm with 3D shape (#15075)

2026-03-18 22:15:24 -07:00

numa_utils.cpp

[CPU] improve numa memory binding (#19666)

2026-03-18 22:15:50 -07:00

qkv_proj.cpp

…

rope.cpp

[CPU] Add mrope kernel for Qwen3-vl (#12531)

2026-03-18 22:12:48 -07:00

shm.cpp

…

shm.h

…

topk.cpp

…

torch_extension_cpu.cpp

optimize conv3d used in patch embedding (#16040)

2026-03-18 22:17:53 -07:00

vec_pack.h

…

vec.h

…