I've spun up a gpu_1x_a10 instance on LambdaLabs and followed the instructions in the README (note: espeak package was not found). When trying to run sudo cog run --debug exec I get the following
sudo cog run --debug exec
⚠ Cog doesn't know if CUDA 11.7 is compatible with PyTorch 2.0.0. This might cause CUDA problems.
Setting CuDNN to version 11.7
Building Docker image from environment in cog.yaml...
$ docker build --file - --build-arg BUILDKIT_INLINE_CACHE=1 --tag cog-cog-llama-base --progress auto .
[+] Building 0.7s (22/22) FINISHED
=> [internal] load build definition from Dockerfile 0.0s
=> => transferring dockerfile: 2.25kB 0.0s
=> [internal] load .dockerignore 0.0s
=> => transferring context: 117B 0.0s
=> resolve image config for docker.io/docker/dockerfile:1.2 0.3s
=> CACHED docker-image://docker.io/docker/dockerfile:1.2@sha256:e2a8561e419ab1ba6b2fe6cbdf49fd92b95912df1cf7d31 0.0s
=> [internal] load build definition from Dockerfile 0.0s
=> [internal] load .dockerignore 0.0s
=> [internal] load metadata for docker.io/nvidia/cuda:11.7.0-cudnn8-devel-ubuntu22.04 0.3s
=> [stage-0 1/12] FROM docker.io/nvidia/cuda:11.7.0-cudnn8-devel-ubuntu22.04@sha256:de480887e91e99fffd701a96cf 0.0s
=> [internal] load build context 0.0s
=> => transferring context: 42.02kB 0.0s
=> CACHED [stage-0 2/12] RUN --mount=type=cache,target=/var/cache/apt set -eux; apt-get update -qq; apt-get in 0.0s
=> CACHED [stage-0 3/12] RUN --mount=type=cache,target=/var/cache/apt apt-get update -qq && apt-get install -q 0.0s
=> CACHED [stage-0 4/12] RUN curl -s -S -L https://raw.githubusercontent.com/pyenv/pyenv-installer/master/bin/ 0.0s
=> CACHED [stage-0 5/12] COPY .cog/tmp/build1125054233/cog-0.0.1.dev-py3-none-any.whl /tmp/cog-0.0.1.dev-py3-n 0.0s
=> CACHED [stage-0 6/12] RUN --mount=type=cache,target=/root/.cache/pip pip install /tmp/cog-0.0.1.dev-py3-non 0.0s
=> CACHED [stage-0 7/12] COPY .cog/tmp/build1125054233/requirements.txt /tmp/requirements.txt 0.0s
=> CACHED [stage-0 8/12] RUN --mount=type=cache,target=/root/.cache/pip pip install -r /tmp/requirements.txt 0.0s
=> CACHED [stage-0 9/12] RUN pip install git+https://github.com/huggingface/transformers.git@786092a35e18154ca 0.0s
=> CACHED [stage-0 10/12] RUN mkdir /gc && cd /gc && curl -O https://dl.google.com/dl/cloudsdk/channels/rapid/d 0.0s
=> CACHED [stage-0 11/12] RUN pip install google-cloud-storage 0.0s
=> CACHED [stage-0 12/12] WORKDIR /src 0.0s
=> preparing layers for inline cache 0.0s
=> exporting to image 0.0s
=> => exporting layers 0.0s
=> => writing image sha256:b64feac476a508869e0829238cf9baba9275e5f253ce0a4281c6e20d87ff5018 0.0s
=> => naming to docker.io/library/cog-cog-llama-base 0.0s
Running 'exec' in Docker with the current directory mounted as a volume...
$ docker run --rm --shm-size 8G --gpus all --interactive --tty --mount type=bind,source=/home/ubuntu/cog-llama,destination=/src --workdir /src cog-cog-llama-base exec
[FATAL tini (7)] exec exec failed: No such file or directory
ⅹ exit status 127
Thanks for opening this @josephpconley! That command should be:
`cog run bash`
Also, I'm in the process of updating the README for this repo. With regarding to configuring your environment, this repo should provide a quicker setup. E.g., this cog.yaml will install the dependencies you need.
I've spun up a gpu_1x_a10 instance on LambdaLabs and followed the instructions in the README (note: espeak package was not found). When trying to run
sudo cog run --debug exec
I get the following