check-in fastertransformer (#7)

* add ft code * gitignore * fix lint * revert fmha

check-in fastertransformer (#7)
* add ft code * gitignore * fix lint * revert fmha
9efcac38 · Li Zhang · GitHub · 720fc533 · 9efcac38 · 9efcac38
Unverified Commit 9efcac38 authored Jun 20, 2023 by Li Zhang Committed by GitHub Jun 20, 2023
20 changed files
--- a/src/fastertransformer/layers/attention_layers_int8/AttentionINT8Weight.h
+++ b/src/fastertransformer/layers/attention_layers_int8/AttentionINT8Weight.h
--- a/src/fastertransformer/layers/attention_layers_int8/CMakeLists.txt
+++ b/src/fastertransformer/layers/attention_layers_int8/CMakeLists.txt
--- a/src/fastertransformer/layers/beam_search_layers/BaseBeamSearchLayer.cu
+++ b/src/fastertransformer/layers/beam_search_layers/BaseBeamSearchLayer.cu
--- a/src/fastertransformer/layers/beam_search_layers/BaseBeamSearchLayer.h
+++ b/src/fastertransformer/layers/beam_search_layers/BaseBeamSearchLayer.h
--- a/src/fastertransformer/layers/beam_search_layers/BeamSearchLayer.cu
+++ b/src/fastertransformer/layers/beam_search_layers/BeamSearchLayer.cu
--- a/src/fastertransformer/layers/beam_search_layers/BeamSearchLayer.h
+++ b/src/fastertransformer/layers/beam_search_layers/BeamSearchLayer.h
--- a/src/fastertransformer/layers/beam_search_layers/CMakeLists.txt
+++ b/src/fastertransformer/layers/beam_search_layers/CMakeLists.txt
--- a/src/fastertransformer/layers/beam_search_layers/OnlineBeamSearchLayer.cu
+++ b/src/fastertransformer/layers/beam_search_layers/OnlineBeamSearchLayer.cu
--- a/src/fastertransformer/layers/beam_search_layers/OnlineBeamSearchLayer.h
+++ b/src/fastertransformer/layers/beam_search_layers/OnlineBeamSearchLayer.h
--- a/src/fastertransformer/layers/sampling_layers/BaseSamplingLayer.cc
+++ b/src/fastertransformer/layers/sampling_layers/BaseSamplingLayer.cc
--- a/src/fastertransformer/layers/sampling_layers/BaseSamplingLayer.h
+++ b/src/fastertransformer/layers/sampling_layers/BaseSamplingLayer.h
--- a/src/fastertransformer/layers/sampling_layers/CMakeLists.txt
+++ b/src/fastertransformer/layers/sampling_layers/CMakeLists.txt
--- a/src/fastertransformer/layers/sampling_layers/TopKSamplingLayer.cu
+++ b/src/fastertransformer/layers/sampling_layers/TopKSamplingLayer.cu
--- a/src/fastertransformer/layers/sampling_layers/TopKSamplingLayer.h
+++ b/src/fastertransformer/layers/sampling_layers/TopKSamplingLayer.h
--- a/src/fastertransformer/layers/sampling_layers/TopPSamplingLayer.cu
+++ b/src/fastertransformer/layers/sampling_layers/TopPSamplingLayer.cu
--- a/src/fastertransformer/layers/sampling_layers/TopPSamplingLayer.h
+++ b/src/fastertransformer/layers/sampling_layers/TopPSamplingLayer.h
--- a/src/fastertransformer/models/BaseWeight.h
+++ b/src/fastertransformer/models/BaseWeight.h
--- a/src/fastertransformer/models/CMakeLists.txt
+++ b/src/fastertransformer/models/CMakeLists.txt
--- a/src/fastertransformer/models/llama/Barrier.h
+++ b/src/fastertransformer/models/llama/Barrier.h
--- a/src/fastertransformer/models/llama/CMakeLists.txt
+++ b/src/fastertransformer/models/llama/CMakeLists.txt