Closed freQuensy23-coder closed 2 weeks ago
This is likely related to your CUDA installation. Make sure:
which gcc-12
to confirm you actually have it.pip
can't automatically get the right version from just the requirements file.I recommend developing in a container. Here is my Dockerfile:
FROM pytorch/pytorch:2.3.0-cuda12.1-cudnn8-devel
RUN apt-get update
RUN apt-get install -y git
WORKDIR /workspace/exl2
RUN git clone https://github.com/turboderp/exllamav2.git .
RUN pip install -r requirements.txt
ENV CUDA_HOME=/usr/local/cuda/
ENV TORCH_CUDA_ARCH_LIST="7.5"
RUN pip install .
Closing some stale issues
I'm having trouble working with the ads.
Code:
throws an error:
Full exception message here - https://gist.github.com/freQuensy23-coder/5faf1836f7aa007f6b58b32fb8c0c2d5
Steps to reproduce: 1) Create new conda env 2) clone exllama 2 repo 3) pip install -r requirements 4) pip install . (or EXLLAMA_NOCOMPILE= pip install . same error too)
Nvidia smi returns: `` Thu May 9 18:47:29 2024
+---------------------------------------------------------------------------------------+ | NVIDIA-SMI 535.171.04 Driver Version: 535.171.04 CUDA Version: 12.2 | |-----------------------------------------+----------------------+----------------------+ | GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC | | Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. | | | | MIG M. | |=========================================+======================+======================| | 0 NVIDIA A100 80GB PCIe Off | 00000000:B1:00.0 Off | 0 | | N/A 51C P0 86W / 300W | 17667MiB / 81920MiB | 5% Default | | | | Disabled | +-----------------------------------------+----------------------+----------------------+
+---------------------------------------------------------------------------------------+