environment configuration
envgap__LatentActionPretraining__LAPA-36
Original GitHub issue ↗Opened 2025-04-03
01 / FAILURE SIGNATURE
As reported upstream
At this point, I get the following error:
Not a benchmark task.
- No curated issue-specific recipe or verified environment fix is available.
02 / ENVIRONMENT RECIPE
- Base commit
Not freshly verified- Manifest
requirements.txt- Reproduce
Awaiting issue-specific recipe- Run under trace
Awaiting a meaningful runtime command
03 / ORIGINAL ISSUE TEXT
LatentActionPretraining/LAPA #36 · read the original issue
This is my complete process of configuring the environment, I hope it can be helpful to you ### 1. programming environment setup with cuda: 12.2 ``` conda create -n lapaTemp python=3.10 -y conda activate lapaTemp ``` Then clone the code: `git clone https://github.com/LatentActionPretraining/LAPA.git ` Remove the jax installation from the original project. The new documents `requirement.txt` are as follows: ``` git+https://github.com/lhao499/tux.git flax==0.7.0 optax==0.1.7 chex==0.1.82 einops transformers==4.29.2 datasets==2.13.0 tqdm ml_collections wandb gcsfs requests typing-extensions sentencepiece Pillow ipdb imageio[ffmpeg] decord tiktoken tensorflow[and-cuda] scipy==1.12.0 albumentations uvicorn fastapi ``` execution instruction ```pip install -r requirements.txt ``` Then installation jax/jaxlib: ```pip install --upgrade jax==0.4.23 jaxlib==0.4.23+cuda12.cudnn89 -f https://storage.googleapis.com/jax-releases/jax_cuda_releases.html``` At this point, I get the following error: > (lapaTemp) lyd@zkyd:/data/lyd/workspace/LAPA$ pip install --upgrade jax==0.4.23 jaxlib==0.4.23+cuda12.cudnn89 -f https://storage.googleapis.com/jax-releases/jax_cuda_releases.html > Looking in indexes: https://pypi.tuna.tsinghua.edu.cn/simple > Looking in links: https://storage.googleapis.com/jax-releases/jax_cuda_releases.html > Collecting jax==0.4.23 > Using cached https://pypi.tuna.tsinghua.edu.cn/packages/28/d0/edf653ea02628f2130ea2557f96d02b264768a2f54d22a9c002c7119cb1d/jax-0.4.23-py3-none-any.whl (1.7 MB) > Collecting jaxlib==0.4.23+cuda12.cudnn89 > Using cached https://storage.googleapis.com/jax-releases/cuda12/jaxlib-0.4.23%2Bcuda12.cudnn89-cp310-cp310-manylinux2014_x86_64.whl (131.8 MB) > Requirement already satisfied: ml-dtypes>=0.2.0 in /data/lyd/miniconda3/envs/lapaTemp/lib/python3.10/site-packages (from jax==0.4.23) (0.5.1) > Requirement already satisfied: numpy>=1.22 in /data/lyd/miniconda3/envs/lapaTemp/lib/python3.10/site-packages (from jax==0.4.23) (1.26.4) > Requirement already satisfied: opt-einsum in /data/lyd/miniconda3/envs/lapaTemp/lib/python3.10/site-packages (from jax==0.4.23) (3.4.0) > Requirement already satisfied: scipy>=1.9 in /data/lyd/miniconda3/envs/lapaTemp/lib/python3.10/site-packages (from jax==0.4.23) (1.12.0) > Installing collected packages: jaxlib, jax > Attempting uninstall: jaxlib > Found existing installation: jaxlib 0.5.3 > Uninstalling jaxlib-0.5.3: > Successfully uninstalled jaxlib-0.5.3 > Attempting uninstall: jax > Found existing installation: jax 0.5.3 > Uninstalling jax-0.5.3: > Successfully uninstalled jax-0.5.3 > ERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts. > orbax-checkpoint 0.11.10 requires jax>=0.5.0, but you have jax 0.4.23 which is incompatible. > Successfully installed jax-0.4.23 jaxlib-0.4.23+cuda12.cudnn89 The orbax-checkpoint 0.11.10 version
04 / LABELS
Labels from the report text only; not yet run
No supported category has been assigned.
Label rules and the text that matched
[]
Issue-specific recipe and runtime smoke command require review against the complete issue and repository.
Legacy already_works is install-only; proposed control still requires runtime verification.