FunctionGemma: Conversion to .litertlm for on-device deployment - unable to install dependencies #274
Description
Description of the bug:
Results in
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.
tensorflow-decision-forests 1.12.0 requires tensorflow==2.19.0, which is not installed.
ipython 7.34.0 requires jedi>=0.16, which is not installed.
dopamine-rl 4.1.2 requires tensorflow>=2.2.0, which is not installed.
google-colab 1.0.0 requires requests==2.32.4, but you have requests 2.32.5 which is incompatible.
datasets 4.0.0 requires fsspec[http]<=2025.3.0,>=2023.1.0, but you have fsspec 2025.12.0 which is incompatible.
bigframes 2.31.0 requires rich<14,>=12.4.4, but you have rich 14.2.0 which is incompatible.
opencv-python-headless 4.12.0.88 requires numpy<2.3.0,>=2; python_version >= "3.9", but you have numpy 2.4.0 which is incompatible.
grpcio-status 1.71.2 requires protobuf<6.0dev,>=5.26.1, but you have protobuf 6.33.2 which is incompatible.
google-ai-generativelanguage 0.6.15 requires protobuf!=4.21.0,!=4.21.1,!=4.21.2,!=4.21.3,!=4.21.4,!=4.21.5,<6.0.0dev,>=3.20.2, but you have protobuf 6.33.2 which is incompatible.
gradio 5.50.0 requires pillow<12.0,>=8.0, but you have pillow 12.0.0 which is incompatible.
opencv-python 4.12.0.88 requires numpy<2.3.0,>=2; python_version >= "3.9", but you have numpy 2.4.0 which is incompatible.
torchaudio 2.9.0+cu126 requires torch==2.9.0, but you have torch 2.9.1 which is incompatible.
torchvision 0.24.0+cu126 requires torch==2.9.0, but you have torch 2.9.1 which is incompatible.
opencv-contrib-python 4.12.0.88 requires numpy<2.3.0,>=2; python_version >= "3.9", but you have numpy 2.4.0 which is incompatible.
numba 0.60.0 requires numpy<2.1,>=1.22, but you have numpy 2.4.0 which is incompatible.
gcsfs 2025.3.0 requires fsspec==2025.3.0, but you have fsspec 2025.12.0 which is incompatible.
Successfully installed MarkupSafe-3.0.3 absl-py-2.3.1 ai-edge-litert-nightly-2.2.0.dev20251225 ai-edge-quantizer-nightly-0.5.0.dev20251226 ai-edge-torch-nightly-0.8.0.dev20251226 astunparse-1.6.3 backports.strenum-1.2.8 certifi-2025.11.12 charset_normalizer-3.4.4 filelock-3.20.1 flatbuffers-25.12.19 fsspec-2025.12.0 gast-0.7.0 google_pasta-0.2.0 grpcio-1.76.0 h5py-3.14.0 hf-xet-1.2.0 huggingface-hub-0.36.0 idna-3.11 immutabledict-4.2.2 iniconfig-2.3.0 jax-0.8.2 jaxlib-0.8.2 jinja2-3.1.6 kagglehub-0.3.13 keras-nightly-3.14.0.dev2025122604 libclang-18.1.1 markdown-3.10 markdown-it-py-4.0.0 mdurl-0.1.2 ml_dtypes-0.5.4 mpmath-1.3.0 multipledispatch-1.0.0 namex-0.1.0 networkx-3.6.1 numpy-2.4.0 nvidia-cublas-cu12-12.8.4.1 nvidia-cuda-cupti-cu12-12.8.90 nvidia-cuda-nvrtc-cu12-12.8.93 nvidia-cuda-runtime-cu12-12.8.90 nvidia-cudnn-cu12-9.10.2.21 nvidia-cufft-cu12-11.3.3.83 nvidia-cufile-cu12-1.13.1.3 nvidia-curand-cu12-10.3.9.90 nvidia-cusolver-cu12-11.7.3.90 nvidia-cusparse-cu12-12.5.8.93 nvidia-cusparselt-cu12-0.7.1 nvidia-nccl-cu12-2.27.5 nvidia-nvjitlink-cu12-12.8.93 nvidia-nvshmem-cu12-3.3.20 nvidia-nvtx-cu12-12.8.90 opt_einsum-3.4.0 optree-0.18.0 packaging-25.0 pillow-12.0.0 pluggy-1.6.0 protobuf-6.33.2 pygments-2.19.2 pytest-9.0.2 pyyaml-6.0.3 regex-2025.11.3 requests-2.32.5 rich-14.2.0 safetensors-0.7.0 scipy-1.16.3 setuptools-80.9.0 six-1.17.0 sympy-1.14.0 tabulate-0.9.0 tb-nightly-2.20.0a20250717 tensorboard-data-server-0.7.2 termcolor-3.2.0 tf-nightly-2.21.0.dev20251225 tokenizers-0.22.1 torch-2.9.1 torch-xla2-0.0.1.dev202412041639 tqdm-4.67.1 transformers-4.57.3 triton-3.5.1 typing_extensions-4.15.0 urllib3-2.6.2 werkzeug-3.1.4 wheel-0.45.1 wrapt-2.0.1
WARNING: The following packages were previously imported in this runtime:
[PIL,_distutils_hack,certifi,google,numpy,packaging,six]
You must restart the runtime in order to use newly installed versions.
Actual vs expected behavior:
No response
Any other information you'd like to share?
No response