vllm/csrc/punica/bgmv/bgmv_bf16_bf16_bf16.cu
Austin Veselka eefeb16464
[Kernel] Full Tensor Parallelism for LoRA Layers (#3524)
Co-authored-by: Antoni Baum <antoni.baum@protonmail.com>
2024-04-27 00:03:48 -07:00

6 lines
214 B
Plaintext

#include "bgmv_config.h"
#include "bgmv_impl.cuh"
FOR_BGMV_WIDE_NARROW(INST_BGMV_TWOSIDE, nv_bfloat16, nv_bfloat16, nv_bfloat16)
FOR_INST_BGMV_WIDE_NARROW(INST_BGMV_ONESIDE, nv_bfloat16, nv_bfloat16, nv_bfloat16)