YanbingJiang 1fe691a429 Fix FP8 block quantization when N or K is not multiples of 128 (#8648)

2025-08-01 15:57:19 -07:00

..

activation.cpp

…

bmm.cpp

…

CMakeLists.txt

[CPU] [FP8] set SGLANG_CPU_FP8_CVT_FTZ in CMakeLists.txt (#7885)

2025-07-09 01:53:53 -07:00

common.h

…

decode.cpp

…

extend.cpp

…

gemm_fp8.cpp

…

gemm_int8.cpp

…

gemm.cpp

…

gemm.h

…

interface.cpp

…

moe_fp8.cpp

…

moe_int8.cpp

…

moe.cpp

Fix FP8 block quantization when N or K is not multiples of 128 (#8648)

2025-08-01 15:57:19 -07:00

norm.cpp

…

numa_utils.cpp

…

qkv_proj.cpp

…

rope.cpp

…

shm.cpp

…

shm.h

…

topk.cpp

…

torch_extension_cpu.cpp

…

vec.h

…