Skip to content

GitLab

Switch branch/tag
Find file Normal viewHistoryPermalink
CMakeLists.txt 1.1 KB
Newer Older
Li Zhang's avatar
check-in fastertransformer (#7)  
Li Zhang committed
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40 
# Copyright (c) OpenMMLab. All rights reserved.

cmake_minimum_required(VERSION 3.8)

add_subdirectory(fused_multi_head_attention)

add_library(Llama STATIC 
        LlamaV2.cc
        LlamaBatch.cc
        LlamaCacheManager.cc
        LlamaContextDecoder.cc
        LlamaContextAttentionLayer.cc
        LlamaDecoderSelfAttentionLayer.cc
        LlamaDecoder.cc
        LlamaWeight.cc
        LlamaDecoderLayerWeight.cc
        LlamaFfnLayer.cc
        llama_kernels.cu
        llama_decoder_kernels.cu
        llama_utils.cu)
set_property(TARGET Llama PROPERTY POSITION_INDEPENDENT_CODE  ON)
set_property(TARGET Llama PROPERTY CUDA_RESOLVE_DEVICE_SYMBOLS  ON)
target_link_libraries(Llama PUBLIC -lcudart
        cublasMMWrapper
        DynamicDecodeLayer
        BaseBeamSearchLayer
        activation_kernels
        decoder_masked_multihead_attention
        bert_preprocess_kernels
        decoding_kernels
        unfused_attention_kernels
        custom_ar_kernels
        custom_ar_comm
        gpt_kernels
        tensor
        memory_utils
        nccl_utils
        cuda_utils
        logger
        llama_fmha)