Giters

intel / ipex-llm

Accelerate local LLM inference and finetuning (LLaMA, Mistral, ChatGLM, Qwen, DeepSeek, Mixtral, Gemma, Phi, MiniCPM, Qwen-VL, MiniCPM-V, etc.) on Intel XPU (e.g., local PC with iGPU and NPU, discrete GPU such as Arc, Flex and Max); seamlessly integrate with llama.cpp, Ollama, HuggingFace, LangChain, LlamaIndex, vLLM, DeepSpeed, Axolotl, etc.

Repository from Github https://github.comintel/ipex-llmRepository from Github https://github.comintel/ipex-llm

failed to load Qwen2-VL with ipex-llm[xpu] under a760

Zhiwei-Lii opened this issue · comments

commented

Describe the bug
/usr/local/lib/python3.11/dist-packages/torchvision/io/image.py:13: UserWarning: Failed to load image Python extension: ''If you don't plan on using image functionality from torchvision.io, you can ignore this warning. Otherwise, there might be something wrong with your environment. Did you have libjpeg or libpng installed before building torchvision from source?
warn(
Traceback (most recent call last):
File "/home/llm/llama3_8b_ipex.py", line 7, in
from ipex_llm import optimize_model
File "/usr/local/lib/python3.11/dist-packages/ipex_llm/init.py", line 38, in
ipex_importer.import_ipex()
File "/usr/local/lib/python3.11/dist-packages/ipex_llm/utils/ipex_importer.py", line 136, in import_ipex
self.directly_import_ipex()
File "/usr/local/lib/python3.11/dist-packages/ipex_llm/utils/ipex_importer.py", line 156, in directly_import_ipex
import intel_extension_for_pytorch as ipex
File "/usr/local/lib/python3.11/dist-packages/intel_extension_for_pytorch/init.py", line 122, in
from . import _dynamo
File "/usr/local/lib/python3.11/dist-packages/intel_extension_for_pytorch/_dynamo/init.py", line 5, in
from torch._inductor import codecache # noqa
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/dist-packages/torch/_inductor/codecache.py", line 1437, in
AsyncCompile.warm_pool()
File "/usr/local/lib/python3.11/dist-packages/torch/_inductor/codecache.py", line 1356, in warm_pool
pool = cls.process_pool()
^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/dist-packages/torch/_inductor/codecache.py", line 1341, in process_pool
pool = ProcessPoolExecutor(
^^^^^^^^^^^^^^^^^^^^
File "/usr/lib/python3.11/concurrent/futures/process.py", line 706, in init
self._call_queue = _SafeQueue(
^^^^^^^^^^^
File "/usr/lib/python3.11/concurrent/futures/process.py", line 168, in init
super().init(max_size, ctx=ctx)
File "/usr/lib/python3.11/multiprocessing/queues.py", line 43, in init
self._rlock = ctx.Lock()
^^^^^^^^^^
File "/usr/lib/python3.11/multiprocessing/context.py", line 68, in Lock
return Lock(ctx=self.get_context())
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/lib/python3.11/multiprocessing/synchronize.py", line 162, in init
SemLock.init(self, SEMAPHORE, 1, 1, ctx=ctx)
File "/usr/lib/python3.11/multiprocessing/synchronize.py", line 57, in init
sl = self._semlock = _multiprocessing.SemLock(
^^^^^^^^^^^^^^^^^^^^^^^^^
FileNotFoundError: [Errno 2] No such file or directory

How to reproduce
fail at "from ipex_llm import optimize_model"
don't know which file is required here

Environment information
Following https://github.com/intel/ipex-llm/blob/main/python/llm/example/GPU/HuggingFace/Multimodal/qwen2-vl/README.md
except "conda create -n llm python=3.11; conda activate llm"

Additional context
Add any other context about the problem here.

commented

In my linux, it does not such path "/dev/shm", which used by python library. so it crashed.
critical log: newfstatat(AT_FDCWD, "/dev/shm/sem.EplO0X", 0x7ffdc05ed780, AT_SYMLINK_NOFOLLOW) = -1 ENOENT (No such file or directory)
openat(AT_FDCWD, "/dev/shm/sem.EplO0X", O_RDWR|O_CREAT|O_EXCL, 0600) = -1 ENOENT (No such file or directory)