run openblas docker, when token exceed 50, will crash

[abc20220327]

i use dockfile of openblas_simple , i build the docker image llamapython-cpu ,and run it
command is :
sudo docker run --rm -it -p 8000:8000 -v /home/cd/ai/baichuan/baichuan-ggml:/models -e MODEL=/models/ggml-model-q4_0.bin llamapython-cpu

i use postman to post a request， it can run fine， but when send a message token>50, it will throw error and stop：

I have 64g of ram, I confirmed that I have enough ram, so it's definitely not a problem of insufficient memory, and when I don't use openblas, there is no such problem.

i don't know why, thanks for your good job!

[abc20220327]

dockfile content is:

FROM python:3-slim-bullseye

We need to set the host to 0.0.0.0 to allow outside access

ENV HOST 0.0.0.0

COPY . .

Install the package

RUN apt update && apt install -y libopenblas-dev ninja-build build-essential
RUN python -m pip install --upgrade pip pytest cmake scikit-build setuptools fastapi uvicorn sse-starlette

RUN LLAMA_OPENBLAS=1 pip install llama_cpp_python --verbose

Run the server

CMD python3 -m llama_cpp.server