Chunyuan WU 3ded6235c9 Add fp8 fused_experts kernel for CPU in sgl-kernel and add UT (#6404)

2025-05-23 02:01:55 -07:00

..

activation.cpp

…

bmm.cpp

[CPU] Fix build issue (#6419)

2025-05-21 11:17:10 -07:00

CMakeLists.txt

[CPU] Fix build issue (#6419)

2025-05-21 11:17:10 -07:00

common.h

…

decode.cpp

Update extend/decode attention kernel for CPU in sgl-kernel and add UTs (#6405)

2025-05-19 21:23:17 -07:00

extend.cpp

…

gemm_fp8.cpp

[CPU] Fix build issue (#6419)

2025-05-21 11:17:10 -07:00

gemm_int8.cpp

[CPU] Fix build issue (#6419)

2025-05-21 11:17:10 -07:00

gemm.cpp

[CPU] Fix build issue (#6419)

2025-05-21 11:17:10 -07:00

gemm.h

Add fp8 fused_experts kernel for CPU in sgl-kernel and add UT (#6404)

2025-05-23 02:01:55 -07:00

interface.cpp

[CPU] Fix build issue (#6419)

2025-05-21 11:17:10 -07:00

moe_fp8.cpp

Add fp8 fused_experts kernel for CPU in sgl-kernel and add UT (#6404)

2025-05-23 02:01:55 -07:00

moe_int8.cpp

…

moe.cpp

Add fp8 fused_experts kernel for CPU in sgl-kernel and add UT (#6404)

2025-05-23 02:01:55 -07:00

norm.cpp

…

qkv_proj.cpp

Add fp8 qkv_proj_with_rope kernel for CPU in sgl-kernel and add UT (#6493)

2025-05-23 00:14:46 -07:00

rope.cpp

…

shm.cpp

…

shm.h

[CPU] Fix build issue (#6419)

2025-05-21 11:17:10 -07:00

topk.cpp

…

torch_extension_cpu.cpp

Add fp8 fused_experts kernel for CPU in sgl-kernel and add UT (#6404)

2025-05-23 02:01:55 -07:00

vec.h

…