-
Notifications
You must be signed in to change notification settings - Fork 1.5k
Description
INFO 11-07 06:43:30 [importing.py:53] Triton module has been replaced with a placeholder.
INFO 11-07 06:43:31 [init.py:239] Automatically detected platform cuda.
ModuleNotFoundError Traceback (most recent call last)
/tmp/ipython-input-720217358.py in <cell line: 0>()
1 from vllm import LLM, SamplingParams
----> 2 from vllm.model_executor.models.deepseek_ocr import NGramPerReqLogitsProcessor
3 from PIL import Image
4
5 # Create model instance
ModuleNotFoundError: No module named 'vllm.model_executor.models.deepseek_ocr'
I tried installations with many different setups including
pip install torch==2.8.0 torchvision==0.23.0 torchaudio==2.8.0 --index-url https://download.pytorch.org/whl/cu126
pip install vllm==0.8.5
pip install -r requirements.txt
pip install flash-attn==2.7.3 --no-build-isolation
And
pip install torch==2.6.0 torchvision==0.21.0 torchaudio==2.6.0 --index-url https://download.pytorch.org/whl/cu118
pip install vllm-0.8.5+cu118-cp38-abi3-manylinux1_x86_64.whl
pip install -r requirements.txt
pip install flash-attn==2.7.3 --no-build-isolation
as well as uv pip install -U vllm --pre --extra-index-url https://wheels.vllm.ai/nightly
But None of them works. It always showed me
ModuleNotFoundError: No module named 'vllm.model_executor.models.deepseek_ocr'