diff --git a/cacheflow/model_executor/models/gpt2.py b/cacheflow/model_executor/models/gpt2.py index 98d95c8cbdec6..97673ca450f68 100644 --- a/cacheflow/model_executor/models/gpt2.py +++ b/cacheflow/model_executor/models/gpt2.py @@ -1,7 +1,6 @@ # coding=utf-8 -# Copyright 2023 The CacheFlow team. # Adapted from https://github.com/huggingface/transformers/blob/v4.28.0/src/transformers/models/gpt2/modeling_gpt2.py -# +# Copyright 2023 The CacheFlow team. # Copyright 2018 The OpenAI Team Authors and HuggingFace Inc. team. # Copyright (c) 2018, NVIDIA CORPORATION. All rights reserved. # diff --git a/cacheflow/model_executor/models/gpt_neox.py b/cacheflow/model_executor/models/gpt_neox.py index c4de1f00122a6..8b074aecca3d3 100644 --- a/cacheflow/model_executor/models/gpt_neox.py +++ b/cacheflow/model_executor/models/gpt_neox.py @@ -1,7 +1,6 @@ # coding=utf-8 -# Copyright 2023 The CacheFlow team. # Adapted from https://github.com/huggingface/transformers/blob/v4.28.0/src/transformers/models/gpt_neox/modeling_gpt_neox.py -# +# Copyright 2023 The CacheFlow team. # Copyright 2022 EleutherAI The HuggingFace Inc. team. All rights reserved. # # Licensed under the Apache License, Version 2.0 (the "License"); diff --git a/cacheflow/model_executor/models/llama.py b/cacheflow/model_executor/models/llama.py index e2698272492aa..f42210c7e0356 100644 --- a/cacheflow/model_executor/models/llama.py +++ b/cacheflow/model_executor/models/llama.py @@ -1,7 +1,6 @@ # coding=utf-8 -# Copyright 2023 The CacheFlow team. # Adapted from https://github.com/huggingface/transformers/blob/v4.28.0/src/transformers/models/llama/modeling_llama.py -# +# Copyright 2023 The CacheFlow team. # Copyright 2022 EleutherAI and the HuggingFace Inc. team. All rights reserved. # # This code is based on EleutherAI's GPT-NeoX library and the GPT-NeoX diff --git a/cacheflow/model_executor/models/opt.py b/cacheflow/model_executor/models/opt.py index 4d6b7c7551fc9..ddb09d42e7bc9 100644 --- a/cacheflow/model_executor/models/opt.py +++ b/cacheflow/model_executor/models/opt.py @@ -1,7 +1,6 @@ # coding=utf-8 -# Copyright 2023 The CacheFlow team. # Adapted from https://github.com/huggingface/transformers/blob/v4.28.0/src/transformers/models/opt/modeling_opt.py -# +# Copyright 2023 The CacheFlow team. # Copyright 2022 The Fairseq Authors and The HuggingFace Inc. team. All rights reserved. # # Licensed under the Apache License, Version 2.0 (the "License"); diff --git a/csrc/attention/attention_generic.cuh b/csrc/attention/attention_generic.cuh index 799f873f462a5..61f3b02ff8a3e 100644 --- a/csrc/attention/attention_generic.cuh +++ b/csrc/attention/attention_generic.cuh @@ -1,3 +1,20 @@ +/* + * Adapted from https://github.com/NVIDIA/FasterTransformer/blob/release/v5.3_tag/src/fastertransformer/kernels/decoder_masked_multihead_attention_utils.h + * Copyright (c) 2023, The CacheFlow team. + * Copyright (c) 2020-2023, NVIDIA CORPORATION. All rights reserved. + * + * Licensed under the Apache License, Version 2.0 (the "License"); + * you may not use this file except in compliance with the License. + * You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ #pragma once #include diff --git a/csrc/attention/attention_kernels.cu b/csrc/attention/attention_kernels.cu index 883f1e8150143..4a17c9afd479c 100644 --- a/csrc/attention/attention_kernels.cu +++ b/csrc/attention/attention_kernels.cu @@ -1,3 +1,20 @@ +/* + * Adapted from https://github.com/NVIDIA/FasterTransformer/blob/release/v5.3_tag/src/fastertransformer/kernels/decoder_masked_multihead_attention/decoder_masked_multihead_attention_template.hpp + * Copyright (c) 2023, The CacheFlow team. + * Copyright (c) 2020-2023, NVIDIA CORPORATION. All rights reserved. + * + * Licensed under the Apache License, Version 2.0 (the "License"); + * you may not use this file except in compliance with the License. + * You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ #include #include diff --git a/csrc/attention/attention_utils.cuh b/csrc/attention/attention_utils.cuh index a4180b171e1d9..e13e4541ec17c 100644 --- a/csrc/attention/attention_utils.cuh +++ b/csrc/attention/attention_utils.cuh @@ -1,3 +1,20 @@ +/* + * Adapted from https://github.com/NVIDIA/FasterTransformer/blob/release/v5.3_tag/src/fastertransformer/kernels/decoder_masked_multihead_attention/decoder_masked_multihead_attention_template.hpp + * Copyright (c) 2023, The CacheFlow team. + * Copyright (c) 2020-2023, NVIDIA CORPORATION. All rights reserved. + * + * Licensed under the Apache License, Version 2.0 (the "License"); + * you may not use this file except in compliance with the License. + * You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ #pragma once #include "attention_dtypes.h" diff --git a/csrc/attention/dtype_bfloat16.cuh b/csrc/attention/dtype_bfloat16.cuh index 1e409296ee584..e6b1c470c40db 100644 --- a/csrc/attention/dtype_bfloat16.cuh +++ b/csrc/attention/dtype_bfloat16.cuh @@ -1,3 +1,21 @@ +/* + * Adapted from https://github.com/NVIDIA/FasterTransformer/blob/release/v5.3_tag/src/fastertransformer/kernels/decoder_masked_multihead_attention/decoder_masked_multihead_attention_template.hpp + * and https://github.com/NVIDIA/FasterTransformer/blob/release/v5.3_tag/src/fastertransformer/kernels/decoder_masked_multihead_attention_utils.h + * Copyright (c) 2023, The CacheFlow team. + * Copyright (c) 2020-2023, NVIDIA CORPORATION. All rights reserved. + * + * Licensed under the Apache License, Version 2.0 (the "License"); + * you may not use this file except in compliance with the License. + * You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ #pragma once #include "attention_generic.cuh" diff --git a/csrc/attention/dtype_float16.cuh b/csrc/attention/dtype_float16.cuh index d2a60353e1163..99a791a6d726c 100644 --- a/csrc/attention/dtype_float16.cuh +++ b/csrc/attention/dtype_float16.cuh @@ -1,3 +1,21 @@ +/* + * Adapted from https://github.com/NVIDIA/FasterTransformer/blob/release/v5.3_tag/src/fastertransformer/kernels/decoder_masked_multihead_attention/decoder_masked_multihead_attention_template.hpp + * and https://github.com/NVIDIA/FasterTransformer/blob/release/v5.3_tag/src/fastertransformer/kernels/decoder_masked_multihead_attention_utils.h + * Copyright (c) 2023, The CacheFlow team. + * Copyright (c) 2020-2023, NVIDIA CORPORATION. All rights reserved. + * + * Licensed under the Apache License, Version 2.0 (the "License"); + * you may not use this file except in compliance with the License. + * You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ #pragma once #include "attention_generic.cuh" diff --git a/csrc/attention/dtype_float32.cuh b/csrc/attention/dtype_float32.cuh index fdb35bf4307d4..d4948b7ac9246 100644 --- a/csrc/attention/dtype_float32.cuh +++ b/csrc/attention/dtype_float32.cuh @@ -1,3 +1,21 @@ +/* + * Adapted from https://github.com/NVIDIA/FasterTransformer/blob/release/v5.3_tag/src/fastertransformer/kernels/decoder_masked_multihead_attention/decoder_masked_multihead_attention_template.hpp + * and https://github.com/NVIDIA/FasterTransformer/blob/release/v5.3_tag/src/fastertransformer/kernels/decoder_masked_multihead_attention_utils.h + * Copyright (c) 2023, The CacheFlow team. + * Copyright (c) 2020-2023, NVIDIA CORPORATION. All rights reserved. + * + * Licensed under the Apache License, Version 2.0 (the "License"); + * you may not use this file except in compliance with the License. + * You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ #pragma once #include "attention_generic.cuh" diff --git a/csrc/reduction_utils.cuh b/csrc/reduction_utils.cuh index 7f904c08698a8..1e080b983889d 100644 --- a/csrc/reduction_utils.cuh +++ b/csrc/reduction_utils.cuh @@ -1,3 +1,20 @@ +/* + * Adapted from https://github.com/NVIDIA/FasterTransformer/blob/release/v5.3_tag/src/fastertransformer/kernels/reduce_kernel_utils.cuh + * Copyright (c) 2023, The CacheFlow team. + * Copyright (c) 2020-2023, NVIDIA CORPORATION. All rights reserved. + * + * Licensed under the Apache License, Version 2.0 (the "License"); + * you may not use this file except in compliance with the License. + * You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ #pragma once namespace cacheflow {