From 4c487313f26b7537f18125a5ede51e1e5dfdd349 Mon Sep 17 00:00:00 2001 From: Qiyuan Gong Date: Fri, 22 Dec 2023 16:38:24 +0800 Subject: [PATCH] Revert "[LLM] IPEX auto importer turn on by default for XPU (#9730)" (#9759) This reverts commit 0284801fbd25ddd9dcc6332d1169defe30858038. --- .../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 + .../Model/aquila/generate.py | 1 + .../Model/aquila2/generate.py | 1 + .../Model/baichuan/generate.py | 1 + .../Model/baichuan2/generate.py | 1 + .../Model/bluelm/generate.py | 1 + .../Model/chatglm2/generate.py | 1 + .../Model/chatglm2/streamchat.py | 1 + .../Model/chatglm3/generate.py | 1 + .../Model/chatglm3/streamchat.py | 1 + .../Model/chinese-llama2/generate.py | 1 + .../Model/codellama/generate.py | 1 + .../Model/distil-whisper/recognize.py | 1 + .../Model/dolly-v1/generate.py | 1 + .../Model/dolly-v2/generate.py | 1 + .../Model/falcon/generate.py | 1 + .../Model/flan-t5/generate.py | 1 + .../Model/gpt-j/generate.py | 1 + .../Model/internlm/generate.py | 1 + .../Model/llama2/generate.py | 1 + .../Model/mistral/generate.py | 1 + .../Model/mixtral/generate.py | 1 + .../HF-Transformers-AutoModels/Model/mpt/generate.py | 1 + .../Model/phi-1_5/generate.py | 1 + .../HF-Transformers-AutoModels/Model/qwen-vl/chat.py | 1 + .../HF-Transformers-AutoModels/Model/qwen/generate.py | 1 + .../Model/replit/generate.py | 1 + .../Model/starcoder/generate.py | 1 + .../Model/vicuna/generate.py | 1 + .../Model/voiceassistant/generate.py | 1 + .../Model/whisper/recognize.py | 1 + .../HF-Transformers-AutoModels/Model/yi/generate.py | 1 + .../More-Data-Types/transformers_low_bit_pipeline.py | 1 + .../GPU/PyTorch-Models/Model/aquila2/generate.py | 1 + .../GPU/PyTorch-Models/Model/baichuan/generate.py | 1 + .../GPU/PyTorch-Models/Model/baichuan2/generate.py | 1 + .../GPU/PyTorch-Models/Model/bluelm/generate.py | 1 + .../GPU/PyTorch-Models/Model/chatglm2/generate.py | 1 + .../GPU/PyTorch-Models/Model/chatglm2/streamchat.py | 1 + .../GPU/PyTorch-Models/Model/chatglm3/generate.py | 1 + .../GPU/PyTorch-Models/Model/chatglm3/streamchat.py | 1 + .../GPU/PyTorch-Models/Model/codellama/generate.py | 1 + .../PyTorch-Models/Model/distil-whisper/recognize.py | 1 + .../GPU/PyTorch-Models/Model/dolly-v1/generate.py | 1 + .../GPU/PyTorch-Models/Model/dolly-v2/generate.py | 1 + .../GPU/PyTorch-Models/Model/flan-t5/generate.py | 1 + .../GPU/PyTorch-Models/Model/llama2/generate.py | 1 + .../Model/llama2/low_memory_generate.py | 1 + .../GPU/PyTorch-Models/Model/llava/generate.py | 1 + .../GPU/PyTorch-Models/Model/mistral/generate.py | 1 + .../GPU/PyTorch-Models/Model/mixtral/generate.py | 1 + .../GPU/PyTorch-Models/Model/phi-1_5/generate.py | 1 + .../example/GPU/PyTorch-Models/Model/qwen-vl/chat.py | 1 + .../GPU/PyTorch-Models/Model/replit/generate.py | 1 + .../GPU/PyTorch-Models/Model/starcoder/generate.py | 1 + .../example/GPU/PyTorch-Models/Model/yi/generate.py | 1 + .../GPU/PyTorch-Models/More-Data-Types/generate.py | 1 + .../example/GPU/PyTorch-Models/Save-Load/generate.py | 1 + .../alpaca-qlora/alpaca_qlora_finetuning.py | 1 + .../example/GPU/QLoRA-FineTuning/qlora_finetuning.py | 1 + python/llm/src/bigdl/llm/__init__.py | 2 +- python/llm/src/bigdl/llm/utils/ipex_importer.py | 11 +---------- 65 files changed, 65 insertions(+), 11 deletions(-) diff --git a/python/llm/example/GPU/Deepspeed-AutoTP/deepspeed_autotp.py b/python/llm/example/GPU/Deepspeed-AutoTP/deepspeed_autotp.py index 1d15c991..6b1309a7 100644 --- a/python/llm/example/GPU/Deepspeed-AutoTP/deepspeed_autotp.py +++ b/python/llm/example/GPU/Deepspeed-AutoTP/deepspeed_autotp.py @@ -25,6 +25,7 @@ world_size = int(os.getenv("WORLD_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 7402a378..136bd35d 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 @@ -17,6 +17,7 @@ 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 af88b2cf..14a61fd8 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 @@ -15,6 +15,7 @@ # 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 0f595d6e..5d77801d 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 @@ -17,6 +17,7 @@ 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 82157269..d070a75c 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 @@ -15,6 +15,7 @@ # 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 44398b9e..e0a88d45 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 @@ -15,6 +15,7 @@ # 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 168b8ca0..7e1e2d0d 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 @@ -15,6 +15,7 @@ # 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 cf03dbab..ebb87ad9 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 @@ -15,6 +15,7 @@ # 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 4f0a4514..c5d35f87 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 @@ -15,6 +15,7 @@ # 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 ffcff0d6..bc69ae6a 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 @@ -15,6 +15,7 @@ # 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 a45f59c5..1177629e 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 @@ -15,6 +15,7 @@ # 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 d79da518..55e529f7 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 @@ -15,6 +15,7 @@ # 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 8a63804c..f294dea9 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 @@ -15,6 +15,7 @@ # 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 865270a9..ca19ff39 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 @@ -15,6 +15,7 @@ # 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 9624458f..4f215739 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 @@ -15,6 +15,7 @@ # 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 67e3cbe4..00a6810e 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 @@ -14,6 +14,7 @@ # 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 bf45d549..75c058b3 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 @@ -15,6 +15,7 @@ # 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 5d6f4da4..d785dec2 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 @@ -15,6 +15,7 @@ # 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 c7ed31cb..0edeb47c 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 @@ -15,6 +15,7 @@ # 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 1b8cddf6..8d6ec148 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 @@ -15,6 +15,7 @@ # 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 0ab6cb3b..fb937216 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 @@ -15,6 +15,7 @@ # 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 3144ce3b..fd035ab6 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 @@ -15,6 +15,7 @@ # 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 e9004612..3959a667 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 @@ -15,6 +15,7 @@ # 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 7f01b358..fcf8cca9 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 @@ -15,6 +15,7 @@ # 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 60421d97..405b18a0 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 @@ -15,6 +15,7 @@ # 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 8b6d833e..647bed99 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 @@ -15,6 +15,7 @@ # 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 bb591336..2108654d 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 @@ -15,6 +15,7 @@ # 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 4781a853..55d1eb47 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 @@ -22,6 +22,7 @@ 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 a588065c..9e998470 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 @@ -15,6 +15,7 @@ # 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 e025249b..9934eda4 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 @@ -15,6 +15,7 @@ # 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 762aea17..1a3b1672 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 @@ -15,6 +15,7 @@ # 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 064e9358..f66d3dce 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 @@ -15,6 +15,7 @@ # 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 3231d7b4..64f9dea4 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 @@ -17,6 +17,7 @@ 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 41729c65..268e78da 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 @@ -15,6 +15,7 @@ # 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 36c8594f..13a9f61f 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 @@ -15,6 +15,7 @@ # 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 7a2f61a5..2b638a91 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 @@ -15,6 +15,7 @@ # 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 3845d842..955fd710 100644 --- a/python/llm/example/GPU/PyTorch-Models/Model/aquila2/generate.py +++ b/python/llm/example/GPU/PyTorch-Models/Model/aquila2/generate.py @@ -15,6 +15,7 @@ # 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 05ec2eca..d8f4642b 100644 --- a/python/llm/example/GPU/PyTorch-Models/Model/baichuan/generate.py +++ b/python/llm/example/GPU/PyTorch-Models/Model/baichuan/generate.py @@ -15,6 +15,7 @@ # 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 d9e0b9a8..ebd052ec 100644 --- a/python/llm/example/GPU/PyTorch-Models/Model/baichuan2/generate.py +++ b/python/llm/example/GPU/PyTorch-Models/Model/baichuan2/generate.py @@ -15,6 +15,7 @@ # 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 aa2369f7..65bc775d 100644 --- a/python/llm/example/GPU/PyTorch-Models/Model/bluelm/generate.py +++ b/python/llm/example/GPU/PyTorch-Models/Model/bluelm/generate.py @@ -15,6 +15,7 @@ # 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 ae97ef25..8520f3b0 100644 --- a/python/llm/example/GPU/PyTorch-Models/Model/chatglm2/generate.py +++ b/python/llm/example/GPU/PyTorch-Models/Model/chatglm2/generate.py @@ -15,6 +15,7 @@ # 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 2ef9c150..18ae779e 100644 --- a/python/llm/example/GPU/PyTorch-Models/Model/chatglm2/streamchat.py +++ b/python/llm/example/GPU/PyTorch-Models/Model/chatglm2/streamchat.py @@ -15,6 +15,7 @@ # 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 f8e41d98..9194310b 100644 --- a/python/llm/example/GPU/PyTorch-Models/Model/chatglm3/generate.py +++ b/python/llm/example/GPU/PyTorch-Models/Model/chatglm3/generate.py @@ -15,6 +15,7 @@ # 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 293a02e1..440db7a6 100644 --- a/python/llm/example/GPU/PyTorch-Models/Model/chatglm3/streamchat.py +++ b/python/llm/example/GPU/PyTorch-Models/Model/chatglm3/streamchat.py @@ -15,6 +15,7 @@ # 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 a95d7d8c..065faade 100644 --- a/python/llm/example/GPU/PyTorch-Models/Model/codellama/generate.py +++ b/python/llm/example/GPU/PyTorch-Models/Model/codellama/generate.py @@ -15,6 +15,7 @@ # 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 2c5326b1..61bda095 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 @@ -14,6 +14,7 @@ # 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 8e93646b..6d096d06 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 @@ -15,6 +15,7 @@ # 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 2dba7581..7b787f02 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 @@ -15,6 +15,7 @@ # 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 c89ecbf1..9dfbabc8 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 @@ -15,6 +15,7 @@ # 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 1fc9028a..13ac5b50 100644 --- a/python/llm/example/GPU/PyTorch-Models/Model/llama2/generate.py +++ b/python/llm/example/GPU/PyTorch-Models/Model/llama2/generate.py @@ -15,6 +15,7 @@ # 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 105e1d5f..32f17329 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 @@ -23,6 +23,7 @@ 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 597814e0..c43312c2 100644 --- a/python/llm/example/GPU/PyTorch-Models/Model/llava/generate.py +++ b/python/llm/example/GPU/PyTorch-Models/Model/llava/generate.py @@ -34,6 +34,7 @@ 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 937a6dcb..6d9a9c1e 100644 --- a/python/llm/example/GPU/PyTorch-Models/Model/mistral/generate.py +++ b/python/llm/example/GPU/PyTorch-Models/Model/mistral/generate.py @@ -15,6 +15,7 @@ # 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 aabfadcc..f969ed47 100644 --- a/python/llm/example/GPU/PyTorch-Models/Model/mixtral/generate.py +++ b/python/llm/example/GPU/PyTorch-Models/Model/mixtral/generate.py @@ -15,6 +15,7 @@ # 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 833922e9..f5f2bae0 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 @@ -15,6 +15,7 @@ # 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 b51ffa71..9e9220f0 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 @@ -22,6 +22,7 @@ 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 c43dc32d..a39bcfca 100644 --- a/python/llm/example/GPU/PyTorch-Models/Model/replit/generate.py +++ b/python/llm/example/GPU/PyTorch-Models/Model/replit/generate.py @@ -15,6 +15,7 @@ # 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 8caf6761..bdaf3b1f 100644 --- a/python/llm/example/GPU/PyTorch-Models/Model/starcoder/generate.py +++ b/python/llm/example/GPU/PyTorch-Models/Model/starcoder/generate.py @@ -15,6 +15,7 @@ # 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 0bafebc1..05ca22cb 100644 --- a/python/llm/example/GPU/PyTorch-Models/Model/yi/generate.py +++ b/python/llm/example/GPU/PyTorch-Models/Model/yi/generate.py @@ -15,6 +15,7 @@ # 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 ddd85a94..4f08a2b5 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 @@ -15,6 +15,7 @@ # 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 b19c3571..47a09d2b 100644 --- a/python/llm/example/GPU/PyTorch-Models/Save-Load/generate.py +++ b/python/llm/example/GPU/PyTorch-Models/Save-Load/generate.py @@ -15,6 +15,7 @@ # 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 1c1e402f..c822bd57 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 @@ -46,6 +46,7 @@ from peft import ( ) from utils.prompter import Prompter +import intel_extension_for_pytorch as ipex from bigdl.llm.transformers import AutoModelForCausalLM # import them from bigdl.llm.transformers.qlora to get a BigDL-LLM compatible Peft model from bigdl.llm.transformers.qlora import get_peft_model, prepare_model_for_kbit_training,\ diff --git a/python/llm/example/GPU/QLoRA-FineTuning/qlora_finetuning.py b/python/llm/example/GPU/QLoRA-FineTuning/qlora_finetuning.py index af22916c..21dbeaad 100644 --- a/python/llm/example/GPU/QLoRA-FineTuning/qlora_finetuning.py +++ b/python/llm/example/GPU/QLoRA-FineTuning/qlora_finetuning.py @@ -19,6 +19,7 @@ import os import transformers from transformers import LlamaTokenizer +import intel_extension_for_pytorch as ipex from peft import LoraConfig from bigdl.llm.transformers.qlora import get_peft_model, prepare_model_for_kbit_training from bigdl.llm.transformers import AutoModelForCausalLM diff --git a/python/llm/src/bigdl/llm/__init__.py b/python/llm/src/bigdl/llm/__init__.py index d13ff443..7dd16cc0 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", 'True').lower() in ('true', '1', 't') +BIGDL_IMPORT_IPEX = os.getenv("BIGDL_IMPORT_IPEX", 'False').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 diff --git a/python/llm/src/bigdl/llm/utils/ipex_importer.py b/python/llm/src/bigdl/llm/utils/ipex_importer.py index bf5f6ff0..aae33188 100644 --- a/python/llm/src/bigdl/llm/utils/ipex_importer.py +++ b/python/llm/src/bigdl/llm/utils/ipex_importer.py @@ -35,19 +35,10 @@ class IPEXImporter: """ # Check if xpu version installed try: - # Check if bigdl-core-xe is installed distribution('bigdl-core-xe') return True except PackageNotFoundError: - # bigdl-core-xe not found - # Check if bigdl-core-xe-21 is installed - try: - distribution('bigdl-core-xe-21') - return True - except PackageNotFoundError: - # bigdl-core-xe not found - return False - return False + return False def import_ipex(self): """