DeepSpeed/csrc/fp_quantizer
Omar Elayan c27483933d
wrap include cuda_bf16.h with ifdef BF16_AVAILABLE (#6520)
2024-09-10 16:08:50 +00:00
..
includes wrap include cuda_bf16.h with ifdef BF16_AVAILABLE (#6520) 2024-09-10 16:08:50 +00:00
fp_quantize.cpp Add fp8-fused gemm kernel (#5764) 2024-07-29 11:07:00 -07:00
fp_quantize.cu wrap include cuda_bf16.h with ifdef BF16_AVAILABLE (#6520) 2024-09-10 16:08:50 +00:00