From 05b681fa85d2656ef04577a6404f36f3ef688eb4 Mon Sep 17 00:00:00 2001 From: Ziteng Zhang <87107332+Jasonzzt@users.noreply.github.com> Date: Thu, 4 Jan 2024 13:33:29 +0800 Subject: [PATCH] [LLM] IPEX auto importer set on by default (#9832) * Set BIGDL_IMPORT_IPEX default to True * Remove import intel_extension_for_pytorch as ipex from GPU example --- python/llm/example/GPU/Deepspeed-AutoTP/deepspeed_autotp.py | 1 - .../Advanced-Quantizations/AWQ/generate.py | 1 - .../Advanced-Quantizations/GGUF/generate.py | 1 - .../Advanced-Quantizations/GPTQ/generate.py | 1 - .../GPU/HF-Transformers-AutoModels/Model/aquila/generate.py | 1 - .../GPU/HF-Transformers-AutoModels/Model/aquila2/generate.py | 1 - .../GPU/HF-Transformers-AutoModels/Model/baichuan/generate.py | 1 - .../GPU/HF-Transformers-AutoModels/Model/baichuan2/generate.py | 1 - .../GPU/HF-Transformers-AutoModels/Model/bluelm/generate.py | 1 - .../GPU/HF-Transformers-AutoModels/Model/chatglm2/generate.py | 1 - .../GPU/HF-Transformers-AutoModels/Model/chatglm2/streamchat.py | 1 - .../GPU/HF-Transformers-AutoModels/Model/chatglm3/generate.py | 1 - .../GPU/HF-Transformers-AutoModels/Model/chatglm3/streamchat.py | 1 - .../HF-Transformers-AutoModels/Model/chinese-llama2/generate.py | 1 - .../GPU/HF-Transformers-AutoModels/Model/codellama/generate.py | 1 - .../Model/distil-whisper/recognize.py | 1 - .../GPU/HF-Transformers-AutoModels/Model/dolly-v1/generate.py | 1 - .../GPU/HF-Transformers-AutoModels/Model/dolly-v2/generate.py | 1 - .../GPU/HF-Transformers-AutoModels/Model/falcon/generate.py | 1 - .../GPU/HF-Transformers-AutoModels/Model/flan-t5/generate.py | 1 - .../GPU/HF-Transformers-AutoModels/Model/gpt-j/generate.py | 1 - .../GPU/HF-Transformers-AutoModels/Model/internlm/generate.py | 1 - .../GPU/HF-Transformers-AutoModels/Model/llama2/generate.py | 1 - .../GPU/HF-Transformers-AutoModels/Model/mistral/generate.py | 1 - .../GPU/HF-Transformers-AutoModels/Model/mixtral/generate.py | 1 - .../GPU/HF-Transformers-AutoModels/Model/mpt/generate.py | 1 - .../GPU/HF-Transformers-AutoModels/Model/phi-1_5/generate.py | 1 - .../GPU/HF-Transformers-AutoModels/Model/qwen-vl/chat.py | 1 - .../GPU/HF-Transformers-AutoModels/Model/qwen/generate.py | 1 - .../GPU/HF-Transformers-AutoModels/Model/replit/generate.py | 1 - .../GPU/HF-Transformers-AutoModels/Model/starcoder/generate.py | 1 - .../GPU/HF-Transformers-AutoModels/Model/vicuna/generate.py | 1 - .../HF-Transformers-AutoModels/Model/voiceassistant/generate.py | 1 - .../GPU/HF-Transformers-AutoModels/Model/whisper/recognize.py | 1 - .../example/GPU/HF-Transformers-AutoModels/Model/yi/generate.py | 1 - .../More-Data-Types/transformers_low_bit_pipeline.py | 1 - python/llm/example/GPU/PyTorch-Models/Model/aquila2/generate.py | 1 - .../llm/example/GPU/PyTorch-Models/Model/baichuan/generate.py | 1 - .../llm/example/GPU/PyTorch-Models/Model/baichuan2/generate.py | 1 - python/llm/example/GPU/PyTorch-Models/Model/bluelm/generate.py | 1 - .../llm/example/GPU/PyTorch-Models/Model/chatglm2/generate.py | 1 - .../llm/example/GPU/PyTorch-Models/Model/chatglm2/streamchat.py | 1 - .../llm/example/GPU/PyTorch-Models/Model/chatglm3/generate.py | 1 - .../llm/example/GPU/PyTorch-Models/Model/chatglm3/streamchat.py | 1 - .../llm/example/GPU/PyTorch-Models/Model/codellama/generate.py | 1 - .../GPU/PyTorch-Models/Model/distil-whisper/recognize.py | 1 - .../llm/example/GPU/PyTorch-Models/Model/dolly-v1/generate.py | 1 - .../llm/example/GPU/PyTorch-Models/Model/dolly-v2/generate.py | 1 - python/llm/example/GPU/PyTorch-Models/Model/flan-t5/generate.py | 1 - python/llm/example/GPU/PyTorch-Models/Model/llama2/generate.py | 1 - .../GPU/PyTorch-Models/Model/llama2/low_memory_generate.py | 1 - python/llm/example/GPU/PyTorch-Models/Model/llava/generate.py | 1 - python/llm/example/GPU/PyTorch-Models/Model/mistral/generate.py | 1 - python/llm/example/GPU/PyTorch-Models/Model/mixtral/generate.py | 1 - python/llm/example/GPU/PyTorch-Models/Model/phi-1_5/generate.py | 1 - python/llm/example/GPU/PyTorch-Models/Model/qwen-vl/chat.py | 1 - python/llm/example/GPU/PyTorch-Models/Model/replit/generate.py | 1 - .../llm/example/GPU/PyTorch-Models/Model/starcoder/generate.py | 1 - python/llm/example/GPU/PyTorch-Models/Model/yi/generate.py | 1 - .../llm/example/GPU/PyTorch-Models/More-Data-Types/generate.py | 1 - python/llm/example/GPU/PyTorch-Models/Save-Load/generate.py | 1 - .../QLoRA-FineTuning/alpaca-qlora/alpaca_qlora_finetuning.py | 1 - python/llm/example/GPU/QLoRA-FineTuning/qlora_finetuning.py | 1 - python/llm/src/bigdl/llm/__init__.py | 2 +- 64 files changed, 1 insertion(+), 64 deletions(-) diff --git a/python/llm/example/GPU/Deepspeed-AutoTP/deepspeed_autotp.py b/python/llm/example/GPU/Deepspeed-AutoTP/deepspeed_autotp.py index 7ccc4014..381217c4 100644 --- a/python/llm/example/GPU/Deepspeed-AutoTP/deepspeed_autotp.py +++ b/python/llm/example/GPU/Deepspeed-AutoTP/deepspeed_autotp.py @@ -33,7 +33,6 @@ world_size = get_int_from_env(["WORLD_SIZE","PMI_SIZE"], "1") from bigdl.llm import optimize_model import torch -import intel_extension_for_pytorch as ipex import time import argparse diff --git a/python/llm/example/GPU/HF-Transformers-AutoModels/Advanced-Quantizations/AWQ/generate.py b/python/llm/example/GPU/HF-Transformers-AutoModels/Advanced-Quantizations/AWQ/generate.py index 136bd35d..7402a378 100644 --- a/python/llm/example/GPU/HF-Transformers-AutoModels/Advanced-Quantizations/AWQ/generate.py +++ b/python/llm/example/GPU/HF-Transformers-AutoModels/Advanced-Quantizations/AWQ/generate.py @@ -17,7 +17,6 @@ import torch import time import argparse -import intel_extension_for_pytorch as ipex from bigdl.llm.transformers import AutoModelForCausalLM from transformers import AutoTokenizer diff --git a/python/llm/example/GPU/HF-Transformers-AutoModels/Advanced-Quantizations/GGUF/generate.py b/python/llm/example/GPU/HF-Transformers-AutoModels/Advanced-Quantizations/GGUF/generate.py index 14a61fd8..af88b2cf 100644 --- a/python/llm/example/GPU/HF-Transformers-AutoModels/Advanced-Quantizations/GGUF/generate.py +++ b/python/llm/example/GPU/HF-Transformers-AutoModels/Advanced-Quantizations/GGUF/generate.py @@ -15,7 +15,6 @@ # import torch -import intel_extension_for_pytorch as ipex import time import argparse diff --git a/python/llm/example/GPU/HF-Transformers-AutoModels/Advanced-Quantizations/GPTQ/generate.py b/python/llm/example/GPU/HF-Transformers-AutoModels/Advanced-Quantizations/GPTQ/generate.py index 5d77801d..0f595d6e 100644 --- a/python/llm/example/GPU/HF-Transformers-AutoModels/Advanced-Quantizations/GPTQ/generate.py +++ b/python/llm/example/GPU/HF-Transformers-AutoModels/Advanced-Quantizations/GPTQ/generate.py @@ -17,7 +17,6 @@ import torch import time import argparse -import intel_extension_for_pytorch as ipex from bigdl.llm.transformers import AutoModelForCausalLM from transformers import LlamaTokenizer, GPTQConfig diff --git a/python/llm/example/GPU/HF-Transformers-AutoModels/Model/aquila/generate.py b/python/llm/example/GPU/HF-Transformers-AutoModels/Model/aquila/generate.py index d070a75c..82157269 100644 --- a/python/llm/example/GPU/HF-Transformers-AutoModels/Model/aquila/generate.py +++ b/python/llm/example/GPU/HF-Transformers-AutoModels/Model/aquila/generate.py @@ -15,7 +15,6 @@ # import torch -import intel_extension_for_pytorch as ipex import time import argparse diff --git a/python/llm/example/GPU/HF-Transformers-AutoModels/Model/aquila2/generate.py b/python/llm/example/GPU/HF-Transformers-AutoModels/Model/aquila2/generate.py index e0a88d45..44398b9e 100644 --- a/python/llm/example/GPU/HF-Transformers-AutoModels/Model/aquila2/generate.py +++ b/python/llm/example/GPU/HF-Transformers-AutoModels/Model/aquila2/generate.py @@ -15,7 +15,6 @@ # import torch -import intel_extension_for_pytorch as ipex import time import argparse diff --git a/python/llm/example/GPU/HF-Transformers-AutoModels/Model/baichuan/generate.py b/python/llm/example/GPU/HF-Transformers-AutoModels/Model/baichuan/generate.py index 7e1e2d0d..168b8ca0 100644 --- a/python/llm/example/GPU/HF-Transformers-AutoModels/Model/baichuan/generate.py +++ b/python/llm/example/GPU/HF-Transformers-AutoModels/Model/baichuan/generate.py @@ -15,7 +15,6 @@ # import torch -import intel_extension_for_pytorch as ipex import time import argparse diff --git a/python/llm/example/GPU/HF-Transformers-AutoModels/Model/baichuan2/generate.py b/python/llm/example/GPU/HF-Transformers-AutoModels/Model/baichuan2/generate.py index ebb87ad9..cf03dbab 100644 --- a/python/llm/example/GPU/HF-Transformers-AutoModels/Model/baichuan2/generate.py +++ b/python/llm/example/GPU/HF-Transformers-AutoModels/Model/baichuan2/generate.py @@ -15,7 +15,6 @@ # import torch -import intel_extension_for_pytorch as ipex import time import argparse diff --git a/python/llm/example/GPU/HF-Transformers-AutoModels/Model/bluelm/generate.py b/python/llm/example/GPU/HF-Transformers-AutoModels/Model/bluelm/generate.py index c5d35f87..4f0a4514 100644 --- a/python/llm/example/GPU/HF-Transformers-AutoModels/Model/bluelm/generate.py +++ b/python/llm/example/GPU/HF-Transformers-AutoModels/Model/bluelm/generate.py @@ -15,7 +15,6 @@ # import torch -import intel_extension_for_pytorch as ipex import time import argparse diff --git a/python/llm/example/GPU/HF-Transformers-AutoModels/Model/chatglm2/generate.py b/python/llm/example/GPU/HF-Transformers-AutoModels/Model/chatglm2/generate.py index bc69ae6a..ffcff0d6 100644 --- a/python/llm/example/GPU/HF-Transformers-AutoModels/Model/chatglm2/generate.py +++ b/python/llm/example/GPU/HF-Transformers-AutoModels/Model/chatglm2/generate.py @@ -15,7 +15,6 @@ # import torch -import intel_extension_for_pytorch as ipex import time import argparse import numpy as np diff --git a/python/llm/example/GPU/HF-Transformers-AutoModels/Model/chatglm2/streamchat.py b/python/llm/example/GPU/HF-Transformers-AutoModels/Model/chatglm2/streamchat.py index 1177629e..a45f59c5 100644 --- a/python/llm/example/GPU/HF-Transformers-AutoModels/Model/chatglm2/streamchat.py +++ b/python/llm/example/GPU/HF-Transformers-AutoModels/Model/chatglm2/streamchat.py @@ -15,7 +15,6 @@ # import torch -import intel_extension_for_pytorch as ipex import time import argparse import numpy as np diff --git a/python/llm/example/GPU/HF-Transformers-AutoModels/Model/chatglm3/generate.py b/python/llm/example/GPU/HF-Transformers-AutoModels/Model/chatglm3/generate.py index 55e529f7..d79da518 100644 --- a/python/llm/example/GPU/HF-Transformers-AutoModels/Model/chatglm3/generate.py +++ b/python/llm/example/GPU/HF-Transformers-AutoModels/Model/chatglm3/generate.py @@ -15,7 +15,6 @@ # import torch -import intel_extension_for_pytorch as ipex import time import argparse import numpy as np diff --git a/python/llm/example/GPU/HF-Transformers-AutoModels/Model/chatglm3/streamchat.py b/python/llm/example/GPU/HF-Transformers-AutoModels/Model/chatglm3/streamchat.py index f294dea9..8a63804c 100644 --- a/python/llm/example/GPU/HF-Transformers-AutoModels/Model/chatglm3/streamchat.py +++ b/python/llm/example/GPU/HF-Transformers-AutoModels/Model/chatglm3/streamchat.py @@ -15,7 +15,6 @@ # import torch -import intel_extension_for_pytorch as ipex import time import argparse import numpy as np diff --git a/python/llm/example/GPU/HF-Transformers-AutoModels/Model/chinese-llama2/generate.py b/python/llm/example/GPU/HF-Transformers-AutoModels/Model/chinese-llama2/generate.py index ca19ff39..865270a9 100644 --- a/python/llm/example/GPU/HF-Transformers-AutoModels/Model/chinese-llama2/generate.py +++ b/python/llm/example/GPU/HF-Transformers-AutoModels/Model/chinese-llama2/generate.py @@ -15,7 +15,6 @@ # import torch -import intel_extension_for_pytorch as ipex import time import argparse diff --git a/python/llm/example/GPU/HF-Transformers-AutoModels/Model/codellama/generate.py b/python/llm/example/GPU/HF-Transformers-AutoModels/Model/codellama/generate.py index 4f215739..9624458f 100644 --- a/python/llm/example/GPU/HF-Transformers-AutoModels/Model/codellama/generate.py +++ b/python/llm/example/GPU/HF-Transformers-AutoModels/Model/codellama/generate.py @@ -15,7 +15,6 @@ # import torch -import intel_extension_for_pytorch as ipex import time import argparse diff --git a/python/llm/example/GPU/HF-Transformers-AutoModels/Model/distil-whisper/recognize.py b/python/llm/example/GPU/HF-Transformers-AutoModels/Model/distil-whisper/recognize.py index 00a6810e..67e3cbe4 100644 --- a/python/llm/example/GPU/HF-Transformers-AutoModels/Model/distil-whisper/recognize.py +++ b/python/llm/example/GPU/HF-Transformers-AutoModels/Model/distil-whisper/recognize.py @@ -14,7 +14,6 @@ # limitations under the License. # -import intel_extension_for_pytorch as ipex import time import argparse diff --git a/python/llm/example/GPU/HF-Transformers-AutoModels/Model/dolly-v1/generate.py b/python/llm/example/GPU/HF-Transformers-AutoModels/Model/dolly-v1/generate.py index 75c058b3..bf45d549 100644 --- a/python/llm/example/GPU/HF-Transformers-AutoModels/Model/dolly-v1/generate.py +++ b/python/llm/example/GPU/HF-Transformers-AutoModels/Model/dolly-v1/generate.py @@ -15,7 +15,6 @@ # import torch -import intel_extension_for_pytorch as ipex import time import argparse import numpy as np diff --git a/python/llm/example/GPU/HF-Transformers-AutoModels/Model/dolly-v2/generate.py b/python/llm/example/GPU/HF-Transformers-AutoModels/Model/dolly-v2/generate.py index d785dec2..5d6f4da4 100644 --- a/python/llm/example/GPU/HF-Transformers-AutoModels/Model/dolly-v2/generate.py +++ b/python/llm/example/GPU/HF-Transformers-AutoModels/Model/dolly-v2/generate.py @@ -15,7 +15,6 @@ # import torch -import intel_extension_for_pytorch as ipex import time import argparse import numpy as np diff --git a/python/llm/example/GPU/HF-Transformers-AutoModels/Model/falcon/generate.py b/python/llm/example/GPU/HF-Transformers-AutoModels/Model/falcon/generate.py index 0edeb47c..c7ed31cb 100644 --- a/python/llm/example/GPU/HF-Transformers-AutoModels/Model/falcon/generate.py +++ b/python/llm/example/GPU/HF-Transformers-AutoModels/Model/falcon/generate.py @@ -15,7 +15,6 @@ # import torch -import intel_extension_for_pytorch as ipex import time import argparse diff --git a/python/llm/example/GPU/HF-Transformers-AutoModels/Model/flan-t5/generate.py b/python/llm/example/GPU/HF-Transformers-AutoModels/Model/flan-t5/generate.py index 8d6ec148..1b8cddf6 100644 --- a/python/llm/example/GPU/HF-Transformers-AutoModels/Model/flan-t5/generate.py +++ b/python/llm/example/GPU/HF-Transformers-AutoModels/Model/flan-t5/generate.py @@ -15,7 +15,6 @@ # import torch -import intel_extension_for_pytorch as ipex import time import argparse diff --git a/python/llm/example/GPU/HF-Transformers-AutoModels/Model/gpt-j/generate.py b/python/llm/example/GPU/HF-Transformers-AutoModels/Model/gpt-j/generate.py index fb937216..0ab6cb3b 100644 --- a/python/llm/example/GPU/HF-Transformers-AutoModels/Model/gpt-j/generate.py +++ b/python/llm/example/GPU/HF-Transformers-AutoModels/Model/gpt-j/generate.py @@ -15,7 +15,6 @@ # import torch -import intel_extension_for_pytorch as ipex import time import argparse diff --git a/python/llm/example/GPU/HF-Transformers-AutoModels/Model/internlm/generate.py b/python/llm/example/GPU/HF-Transformers-AutoModels/Model/internlm/generate.py index fd035ab6..3144ce3b 100644 --- a/python/llm/example/GPU/HF-Transformers-AutoModels/Model/internlm/generate.py +++ b/python/llm/example/GPU/HF-Transformers-AutoModels/Model/internlm/generate.py @@ -15,7 +15,6 @@ # import torch -import intel_extension_for_pytorch as ipex import time import argparse diff --git a/python/llm/example/GPU/HF-Transformers-AutoModels/Model/llama2/generate.py b/python/llm/example/GPU/HF-Transformers-AutoModels/Model/llama2/generate.py index 3959a667..e9004612 100644 --- a/python/llm/example/GPU/HF-Transformers-AutoModels/Model/llama2/generate.py +++ b/python/llm/example/GPU/HF-Transformers-AutoModels/Model/llama2/generate.py @@ -15,7 +15,6 @@ # import torch -import intel_extension_for_pytorch as ipex import time import argparse diff --git a/python/llm/example/GPU/HF-Transformers-AutoModels/Model/mistral/generate.py b/python/llm/example/GPU/HF-Transformers-AutoModels/Model/mistral/generate.py index fcf8cca9..7f01b358 100644 --- a/python/llm/example/GPU/HF-Transformers-AutoModels/Model/mistral/generate.py +++ b/python/llm/example/GPU/HF-Transformers-AutoModels/Model/mistral/generate.py @@ -15,7 +15,6 @@ # import torch -import intel_extension_for_pytorch as ipex import time import argparse diff --git a/python/llm/example/GPU/HF-Transformers-AutoModels/Model/mixtral/generate.py b/python/llm/example/GPU/HF-Transformers-AutoModels/Model/mixtral/generate.py index 405b18a0..60421d97 100644 --- a/python/llm/example/GPU/HF-Transformers-AutoModels/Model/mixtral/generate.py +++ b/python/llm/example/GPU/HF-Transformers-AutoModels/Model/mixtral/generate.py @@ -15,7 +15,6 @@ # import torch -import intel_extension_for_pytorch as ipex import time import argparse diff --git a/python/llm/example/GPU/HF-Transformers-AutoModels/Model/mpt/generate.py b/python/llm/example/GPU/HF-Transformers-AutoModels/Model/mpt/generate.py index 647bed99..8b6d833e 100644 --- a/python/llm/example/GPU/HF-Transformers-AutoModels/Model/mpt/generate.py +++ b/python/llm/example/GPU/HF-Transformers-AutoModels/Model/mpt/generate.py @@ -15,7 +15,6 @@ # import torch -import intel_extension_for_pytorch as ipex import time import argparse diff --git a/python/llm/example/GPU/HF-Transformers-AutoModels/Model/phi-1_5/generate.py b/python/llm/example/GPU/HF-Transformers-AutoModels/Model/phi-1_5/generate.py index 2108654d..bb591336 100644 --- a/python/llm/example/GPU/HF-Transformers-AutoModels/Model/phi-1_5/generate.py +++ b/python/llm/example/GPU/HF-Transformers-AutoModels/Model/phi-1_5/generate.py @@ -15,7 +15,6 @@ # import torch -import intel_extension_for_pytorch as ipex import time import argparse import numpy as np diff --git a/python/llm/example/GPU/HF-Transformers-AutoModels/Model/qwen-vl/chat.py b/python/llm/example/GPU/HF-Transformers-AutoModels/Model/qwen-vl/chat.py index 55d1eb47..4781a853 100644 --- a/python/llm/example/GPU/HF-Transformers-AutoModels/Model/qwen-vl/chat.py +++ b/python/llm/example/GPU/HF-Transformers-AutoModels/Model/qwen-vl/chat.py @@ -22,7 +22,6 @@ from transformers import AutoTokenizer from transformers.generation import GenerationConfig from bigdl.llm.transformers import AutoModelForCausalLM -import intel_extension_for_pytorch as ipex torch.manual_seed(1234) diff --git a/python/llm/example/GPU/HF-Transformers-AutoModels/Model/qwen/generate.py b/python/llm/example/GPU/HF-Transformers-AutoModels/Model/qwen/generate.py index 0b898cde..e3b95fba 100644 --- a/python/llm/example/GPU/HF-Transformers-AutoModels/Model/qwen/generate.py +++ b/python/llm/example/GPU/HF-Transformers-AutoModels/Model/qwen/generate.py @@ -15,7 +15,6 @@ # import torch -import intel_extension_for_pytorch as ipex import time import argparse diff --git a/python/llm/example/GPU/HF-Transformers-AutoModels/Model/replit/generate.py b/python/llm/example/GPU/HF-Transformers-AutoModels/Model/replit/generate.py index 9934eda4..e025249b 100644 --- a/python/llm/example/GPU/HF-Transformers-AutoModels/Model/replit/generate.py +++ b/python/llm/example/GPU/HF-Transformers-AutoModels/Model/replit/generate.py @@ -15,7 +15,6 @@ # import torch -import intel_extension_for_pytorch as ipex import time import argparse diff --git a/python/llm/example/GPU/HF-Transformers-AutoModels/Model/starcoder/generate.py b/python/llm/example/GPU/HF-Transformers-AutoModels/Model/starcoder/generate.py index 1a3b1672..762aea17 100644 --- a/python/llm/example/GPU/HF-Transformers-AutoModels/Model/starcoder/generate.py +++ b/python/llm/example/GPU/HF-Transformers-AutoModels/Model/starcoder/generate.py @@ -15,7 +15,6 @@ # import torch -import intel_extension_for_pytorch as ipex import time import argparse diff --git a/python/llm/example/GPU/HF-Transformers-AutoModels/Model/vicuna/generate.py b/python/llm/example/GPU/HF-Transformers-AutoModels/Model/vicuna/generate.py index f66d3dce..064e9358 100644 --- a/python/llm/example/GPU/HF-Transformers-AutoModels/Model/vicuna/generate.py +++ b/python/llm/example/GPU/HF-Transformers-AutoModels/Model/vicuna/generate.py @@ -15,7 +15,6 @@ # import torch -import intel_extension_for_pytorch as ipex import time import argparse diff --git a/python/llm/example/GPU/HF-Transformers-AutoModels/Model/voiceassistant/generate.py b/python/llm/example/GPU/HF-Transformers-AutoModels/Model/voiceassistant/generate.py index 64f9dea4..3231d7b4 100644 --- a/python/llm/example/GPU/HF-Transformers-AutoModels/Model/voiceassistant/generate.py +++ b/python/llm/example/GPU/HF-Transformers-AutoModels/Model/voiceassistant/generate.py @@ -17,7 +17,6 @@ import os import torch import time -import intel_extension_for_pytorch as ipex import argparse import numpy as np import inquirer diff --git a/python/llm/example/GPU/HF-Transformers-AutoModels/Model/whisper/recognize.py b/python/llm/example/GPU/HF-Transformers-AutoModels/Model/whisper/recognize.py index 268e78da..41729c65 100644 --- a/python/llm/example/GPU/HF-Transformers-AutoModels/Model/whisper/recognize.py +++ b/python/llm/example/GPU/HF-Transformers-AutoModels/Model/whisper/recognize.py @@ -15,7 +15,6 @@ # import torch -import intel_extension_for_pytorch as ipex import time import argparse diff --git a/python/llm/example/GPU/HF-Transformers-AutoModels/Model/yi/generate.py b/python/llm/example/GPU/HF-Transformers-AutoModels/Model/yi/generate.py index 214e2904..00f281cb 100644 --- a/python/llm/example/GPU/HF-Transformers-AutoModels/Model/yi/generate.py +++ b/python/llm/example/GPU/HF-Transformers-AutoModels/Model/yi/generate.py @@ -15,7 +15,6 @@ # import torch -import intel_extension_for_pytorch as ipex import time import argparse diff --git a/python/llm/example/GPU/HF-Transformers-AutoModels/More-Data-Types/transformers_low_bit_pipeline.py b/python/llm/example/GPU/HF-Transformers-AutoModels/More-Data-Types/transformers_low_bit_pipeline.py index 2b638a91..7a2f61a5 100644 --- a/python/llm/example/GPU/HF-Transformers-AutoModels/More-Data-Types/transformers_low_bit_pipeline.py +++ b/python/llm/example/GPU/HF-Transformers-AutoModels/More-Data-Types/transformers_low_bit_pipeline.py @@ -15,7 +15,6 @@ # import torch -import intel_extension_for_pytorch as ipex import argparse from bigdl.llm.transformers import AutoModelForCausalLM from transformers import AutoTokenizer, TextGenerationPipeline diff --git a/python/llm/example/GPU/PyTorch-Models/Model/aquila2/generate.py b/python/llm/example/GPU/PyTorch-Models/Model/aquila2/generate.py index 955fd710..3845d842 100644 --- a/python/llm/example/GPU/PyTorch-Models/Model/aquila2/generate.py +++ b/python/llm/example/GPU/PyTorch-Models/Model/aquila2/generate.py @@ -15,7 +15,6 @@ # import torch -import intel_extension_for_pytorch as ipex import time import argparse diff --git a/python/llm/example/GPU/PyTorch-Models/Model/baichuan/generate.py b/python/llm/example/GPU/PyTorch-Models/Model/baichuan/generate.py index d8f4642b..05ec2eca 100644 --- a/python/llm/example/GPU/PyTorch-Models/Model/baichuan/generate.py +++ b/python/llm/example/GPU/PyTorch-Models/Model/baichuan/generate.py @@ -15,7 +15,6 @@ # import torch -import intel_extension_for_pytorch as ipex import time import argparse diff --git a/python/llm/example/GPU/PyTorch-Models/Model/baichuan2/generate.py b/python/llm/example/GPU/PyTorch-Models/Model/baichuan2/generate.py index ebd052ec..d9e0b9a8 100644 --- a/python/llm/example/GPU/PyTorch-Models/Model/baichuan2/generate.py +++ b/python/llm/example/GPU/PyTorch-Models/Model/baichuan2/generate.py @@ -15,7 +15,6 @@ # import torch -import intel_extension_for_pytorch as ipex import time import argparse diff --git a/python/llm/example/GPU/PyTorch-Models/Model/bluelm/generate.py b/python/llm/example/GPU/PyTorch-Models/Model/bluelm/generate.py index 65bc775d..aa2369f7 100644 --- a/python/llm/example/GPU/PyTorch-Models/Model/bluelm/generate.py +++ b/python/llm/example/GPU/PyTorch-Models/Model/bluelm/generate.py @@ -15,7 +15,6 @@ # import torch -import intel_extension_for_pytorch as ipex import time import argparse diff --git a/python/llm/example/GPU/PyTorch-Models/Model/chatglm2/generate.py b/python/llm/example/GPU/PyTorch-Models/Model/chatglm2/generate.py index 8520f3b0..ae97ef25 100644 --- a/python/llm/example/GPU/PyTorch-Models/Model/chatglm2/generate.py +++ b/python/llm/example/GPU/PyTorch-Models/Model/chatglm2/generate.py @@ -15,7 +15,6 @@ # import torch -import intel_extension_for_pytorch as ipex import time import argparse diff --git a/python/llm/example/GPU/PyTorch-Models/Model/chatglm2/streamchat.py b/python/llm/example/GPU/PyTorch-Models/Model/chatglm2/streamchat.py index 18ae779e..2ef9c150 100644 --- a/python/llm/example/GPU/PyTorch-Models/Model/chatglm2/streamchat.py +++ b/python/llm/example/GPU/PyTorch-Models/Model/chatglm2/streamchat.py @@ -15,7 +15,6 @@ # import torch -import intel_extension_for_pytorch as ipex import time import argparse import numpy as np diff --git a/python/llm/example/GPU/PyTorch-Models/Model/chatglm3/generate.py b/python/llm/example/GPU/PyTorch-Models/Model/chatglm3/generate.py index 9194310b..f8e41d98 100644 --- a/python/llm/example/GPU/PyTorch-Models/Model/chatglm3/generate.py +++ b/python/llm/example/GPU/PyTorch-Models/Model/chatglm3/generate.py @@ -15,7 +15,6 @@ # import torch -import intel_extension_for_pytorch as ipex import time import argparse diff --git a/python/llm/example/GPU/PyTorch-Models/Model/chatglm3/streamchat.py b/python/llm/example/GPU/PyTorch-Models/Model/chatglm3/streamchat.py index 440db7a6..293a02e1 100644 --- a/python/llm/example/GPU/PyTorch-Models/Model/chatglm3/streamchat.py +++ b/python/llm/example/GPU/PyTorch-Models/Model/chatglm3/streamchat.py @@ -15,7 +15,6 @@ # import torch -import intel_extension_for_pytorch as ipex import time import argparse import numpy as np diff --git a/python/llm/example/GPU/PyTorch-Models/Model/codellama/generate.py b/python/llm/example/GPU/PyTorch-Models/Model/codellama/generate.py index 065faade..a95d7d8c 100644 --- a/python/llm/example/GPU/PyTorch-Models/Model/codellama/generate.py +++ b/python/llm/example/GPU/PyTorch-Models/Model/codellama/generate.py @@ -15,7 +15,6 @@ # import torch -import intel_extension_for_pytorch as ipex import time import argparse diff --git a/python/llm/example/GPU/PyTorch-Models/Model/distil-whisper/recognize.py b/python/llm/example/GPU/PyTorch-Models/Model/distil-whisper/recognize.py index 61bda095..2c5326b1 100644 --- a/python/llm/example/GPU/PyTorch-Models/Model/distil-whisper/recognize.py +++ b/python/llm/example/GPU/PyTorch-Models/Model/distil-whisper/recognize.py @@ -14,7 +14,6 @@ # limitations under the License. # -import intel_extension_for_pytorch as ipex import time import argparse diff --git a/python/llm/example/GPU/PyTorch-Models/Model/dolly-v1/generate.py b/python/llm/example/GPU/PyTorch-Models/Model/dolly-v1/generate.py index 6d096d06..8e93646b 100644 --- a/python/llm/example/GPU/PyTorch-Models/Model/dolly-v1/generate.py +++ b/python/llm/example/GPU/PyTorch-Models/Model/dolly-v1/generate.py @@ -15,7 +15,6 @@ # import torch -import intel_extension_for_pytorch as ipex import time import argparse diff --git a/python/llm/example/GPU/PyTorch-Models/Model/dolly-v2/generate.py b/python/llm/example/GPU/PyTorch-Models/Model/dolly-v2/generate.py index 7b787f02..2dba7581 100644 --- a/python/llm/example/GPU/PyTorch-Models/Model/dolly-v2/generate.py +++ b/python/llm/example/GPU/PyTorch-Models/Model/dolly-v2/generate.py @@ -15,7 +15,6 @@ # import torch -import intel_extension_for_pytorch as ipex import time import argparse diff --git a/python/llm/example/GPU/PyTorch-Models/Model/flan-t5/generate.py b/python/llm/example/GPU/PyTorch-Models/Model/flan-t5/generate.py index 9dfbabc8..c89ecbf1 100644 --- a/python/llm/example/GPU/PyTorch-Models/Model/flan-t5/generate.py +++ b/python/llm/example/GPU/PyTorch-Models/Model/flan-t5/generate.py @@ -15,7 +15,6 @@ # import torch -import intel_extension_for_pytorch as ipex import time import argparse diff --git a/python/llm/example/GPU/PyTorch-Models/Model/llama2/generate.py b/python/llm/example/GPU/PyTorch-Models/Model/llama2/generate.py index 13ac5b50..1fc9028a 100644 --- a/python/llm/example/GPU/PyTorch-Models/Model/llama2/generate.py +++ b/python/llm/example/GPU/PyTorch-Models/Model/llama2/generate.py @@ -15,7 +15,6 @@ # import torch -import intel_extension_for_pytorch as ipex import time import argparse diff --git a/python/llm/example/GPU/PyTorch-Models/Model/llama2/low_memory_generate.py b/python/llm/example/GPU/PyTorch-Models/Model/llama2/low_memory_generate.py index 32f17329..105e1d5f 100644 --- a/python/llm/example/GPU/PyTorch-Models/Model/llama2/low_memory_generate.py +++ b/python/llm/example/GPU/PyTorch-Models/Model/llama2/low_memory_generate.py @@ -23,7 +23,6 @@ import time import warnings from typing import Dict, List, Optional, Union -import intel_extension_for_pytorch as ipex import torch import torch.nn as nn from accelerate import init_empty_weights diff --git a/python/llm/example/GPU/PyTorch-Models/Model/llava/generate.py b/python/llm/example/GPU/PyTorch-Models/Model/llava/generate.py index c43312c2..597814e0 100644 --- a/python/llm/example/GPU/PyTorch-Models/Model/llava/generate.py +++ b/python/llm/example/GPU/PyTorch-Models/Model/llava/generate.py @@ -34,7 +34,6 @@ import argparse import torch -import intel_extension_for_pytorch as ipex import time from transformers import AutoModelForCausalLM diff --git a/python/llm/example/GPU/PyTorch-Models/Model/mistral/generate.py b/python/llm/example/GPU/PyTorch-Models/Model/mistral/generate.py index 6d9a9c1e..937a6dcb 100644 --- a/python/llm/example/GPU/PyTorch-Models/Model/mistral/generate.py +++ b/python/llm/example/GPU/PyTorch-Models/Model/mistral/generate.py @@ -15,7 +15,6 @@ # import torch -import intel_extension_for_pytorch as ipex import time import argparse diff --git a/python/llm/example/GPU/PyTorch-Models/Model/mixtral/generate.py b/python/llm/example/GPU/PyTorch-Models/Model/mixtral/generate.py index f969ed47..aabfadcc 100644 --- a/python/llm/example/GPU/PyTorch-Models/Model/mixtral/generate.py +++ b/python/llm/example/GPU/PyTorch-Models/Model/mixtral/generate.py @@ -15,7 +15,6 @@ # import torch -import intel_extension_for_pytorch as ipex import time import argparse diff --git a/python/llm/example/GPU/PyTorch-Models/Model/phi-1_5/generate.py b/python/llm/example/GPU/PyTorch-Models/Model/phi-1_5/generate.py index f5f2bae0..833922e9 100644 --- a/python/llm/example/GPU/PyTorch-Models/Model/phi-1_5/generate.py +++ b/python/llm/example/GPU/PyTorch-Models/Model/phi-1_5/generate.py @@ -15,7 +15,6 @@ # import torch -import intel_extension_for_pytorch as ipex import time import argparse diff --git a/python/llm/example/GPU/PyTorch-Models/Model/qwen-vl/chat.py b/python/llm/example/GPU/PyTorch-Models/Model/qwen-vl/chat.py index 9e9220f0..b51ffa71 100644 --- a/python/llm/example/GPU/PyTorch-Models/Model/qwen-vl/chat.py +++ b/python/llm/example/GPU/PyTorch-Models/Model/qwen-vl/chat.py @@ -22,7 +22,6 @@ from transformers import AutoModelForCausalLM, AutoTokenizer from transformers.generation import GenerationConfig from bigdl.llm import optimize_model -import intel_extension_for_pytorch as ipex torch.manual_seed(1234) diff --git a/python/llm/example/GPU/PyTorch-Models/Model/replit/generate.py b/python/llm/example/GPU/PyTorch-Models/Model/replit/generate.py index a39bcfca..c43dc32d 100644 --- a/python/llm/example/GPU/PyTorch-Models/Model/replit/generate.py +++ b/python/llm/example/GPU/PyTorch-Models/Model/replit/generate.py @@ -15,7 +15,6 @@ # import torch -import intel_extension_for_pytorch as ipex import time import argparse diff --git a/python/llm/example/GPU/PyTorch-Models/Model/starcoder/generate.py b/python/llm/example/GPU/PyTorch-Models/Model/starcoder/generate.py index bdaf3b1f..8caf6761 100644 --- a/python/llm/example/GPU/PyTorch-Models/Model/starcoder/generate.py +++ b/python/llm/example/GPU/PyTorch-Models/Model/starcoder/generate.py @@ -15,7 +15,6 @@ # import torch -import intel_extension_for_pytorch as ipex import time import argparse diff --git a/python/llm/example/GPU/PyTorch-Models/Model/yi/generate.py b/python/llm/example/GPU/PyTorch-Models/Model/yi/generate.py index 05ca22cb..0bafebc1 100644 --- a/python/llm/example/GPU/PyTorch-Models/Model/yi/generate.py +++ b/python/llm/example/GPU/PyTorch-Models/Model/yi/generate.py @@ -15,7 +15,6 @@ # import torch -import intel_extension_for_pytorch as ipex import time import argparse diff --git a/python/llm/example/GPU/PyTorch-Models/More-Data-Types/generate.py b/python/llm/example/GPU/PyTorch-Models/More-Data-Types/generate.py index 4f08a2b5..ddd85a94 100644 --- a/python/llm/example/GPU/PyTorch-Models/More-Data-Types/generate.py +++ b/python/llm/example/GPU/PyTorch-Models/More-Data-Types/generate.py @@ -15,7 +15,6 @@ # import torch -import intel_extension_for_pytorch as ipex import time import argparse diff --git a/python/llm/example/GPU/PyTorch-Models/Save-Load/generate.py b/python/llm/example/GPU/PyTorch-Models/Save-Load/generate.py index 47a09d2b..b19c3571 100644 --- a/python/llm/example/GPU/PyTorch-Models/Save-Load/generate.py +++ b/python/llm/example/GPU/PyTorch-Models/Save-Load/generate.py @@ -15,7 +15,6 @@ # import torch -import intel_extension_for_pytorch as ipex import time import argparse from bigdl.llm import optimize_model diff --git a/python/llm/example/GPU/QLoRA-FineTuning/alpaca-qlora/alpaca_qlora_finetuning.py b/python/llm/example/GPU/QLoRA-FineTuning/alpaca-qlora/alpaca_qlora_finetuning.py index cfed03fc..4c9b0421 100644 --- a/python/llm/example/GPU/QLoRA-FineTuning/alpaca-qlora/alpaca_qlora_finetuning.py +++ b/python/llm/example/GPU/QLoRA-FineTuning/alpaca-qlora/alpaca_qlora_finetuning.py @@ -46,7 +46,6 @@ from peft import ( ) from utils.prompter import Prompter -import intel_extension_for_pytorch as ipex from transformers import BitsAndBytesConfig from bigdl.llm.transformers import AutoModelForCausalLM # import them from bigdl.llm.transformers.qlora to get a BigDL-LLM compatible Peft model diff --git a/python/llm/example/GPU/QLoRA-FineTuning/qlora_finetuning.py b/python/llm/example/GPU/QLoRA-FineTuning/qlora_finetuning.py index bab936c5..ac13dbcd 100644 --- a/python/llm/example/GPU/QLoRA-FineTuning/qlora_finetuning.py +++ b/python/llm/example/GPU/QLoRA-FineTuning/qlora_finetuning.py @@ -19,7 +19,6 @@ import os import transformers from transformers import LlamaTokenizer -import intel_extension_for_pytorch as ipex from peft import LoraConfig from transformers import BitsAndBytesConfig from bigdl.llm.transformers.qlora import get_peft_model, prepare_model_for_kbit_training diff --git a/python/llm/src/bigdl/llm/__init__.py b/python/llm/src/bigdl/llm/__init__.py index 7dd16cc0..d13ff443 100644 --- a/python/llm/src/bigdl/llm/__init__.py +++ b/python/llm/src/bigdl/llm/__init__.py @@ -24,7 +24,7 @@ from .optimize import optimize_model import os # Default is false, set to true to auto importing Intel Extension for PyTorch. -BIGDL_IMPORT_IPEX = os.getenv("BIGDL_IMPORT_IPEX", 'False').lower() in ('true', '1', 't') +BIGDL_IMPORT_IPEX = os.getenv("BIGDL_IMPORT_IPEX", 'True').lower() in ('true', '1', 't') if BIGDL_IMPORT_IPEX: # Import Intel Extension for PyTorch as ipex if XPU version is installed from .utils.ipex_importer import ipex_importer