diff --git a/Dockerfile b/Dockerfile index a7c920b9f..b01dd7065 100644 --- a/Dockerfile +++ b/Dockerfile @@ -20,6 +20,7 @@ ENV PATH="/opt/venv/bin:$PATH" # Upgrade pip RUN pip install --upgrade pip +RUN pip install uv RUN pip install git+https://github.com/ayaka14732/jax-smi.git # If you encounter a checkpoint issue, try using following old version of pathways-utils. # RUN pip install git+https://github.com/AI-Hypercomputer/pathways-utils.git@b72729bb152b7b3426299405950b3af300d765a9#egg=pathwaysutils @@ -37,6 +38,27 @@ RUN pip install -e . RUN bash /app/scripts/install_tunix_vllm_requirement.sh +# Build argument to conditionally install MaxText dependencies +ARG INSTALL_MAXTEXT=false + +# Install MaxText specific dependencies conditionally +RUN if [ "$INSTALL_MAXTEXT" = "true" ]; then \ + uv pip install -r /app/requirements/maxtext_requirements.txt --torch-backend=cpu; \ + fi + +# Build argument to conditionally install Raiden weight sync dependencies +ARG INSTALL_RAIDEN=false + +# Install Raiden specific dependencies conditionally +RUN if [ "$INSTALL_RAIDEN" = "true" ]; then \ + if [ -d "/app/raiden_wheels" ] && ls /app/raiden_wheels/*.whl 1>/dev/null 2>&1; then \ + pip install --force-reinstall --no-deps /app/raiden_wheels/*.whl; \ + else \ + pip install keyrings.google-artifactregistry-auth && \ + pip install tpu-raiden-jax --extra-index-url https://us-python.pkg.dev/cloud-tpu-inference-test/tpu-raiden/simple/; \ + fi; \ + fi + # Build argument to conditionally install DeepSWE evaluation dependencies ARG INSTALL_DEEPSWE_DEPS=false diff --git a/requirements/maxtext_requirements.txt b/requirements/maxtext_requirements.txt new file mode 100644 index 000000000..38f0af3a1 --- /dev/null +++ b/requirements/maxtext_requirements.txt @@ -0,0 +1,14 @@ +maxtext @ git+https://github.com/AI-Hypercomputer/maxtext.git@8c2e29218c01b6287ba85e8d0dc9555561f7634c +maxtext-vllm-adapter @ git+https://github.com/AI-Hypercomputer/maxtext.git@8c2e29218c01b6287ba85e8d0dc9555561f7634c#subdirectory=src/maxtext/integration/vllm +aqtp +tokamax>=0.0.4 +drjax>=0.1.4 +ml-goodput-measurement +cloud-accelerator-diagnostics +cloud-tpu-diagnostics +google-cloud-mldiagnostics>=0.5.10 +google-cloud-monitoring +einshape +typeguard +xprof +cheroot diff --git a/requirements/requirements.txt b/requirements/requirements.txt index 7f3f9303d..92c9fd6c6 100644 --- a/requirements/requirements.txt +++ b/requirements/requirements.txt @@ -1,2 +1,2 @@ -vllm @ git+https://github.com/vllm-project/vllm.git@9842d701450214d4b78cd9aefb8eee0c616bce33 +vllm @ git+https://github.com/vllm-project/vllm.git@d626108b1841888ec90aced33367149a6bbc7e4b diff --git a/requirements/special_requirements.txt b/requirements/special_requirements.txt index 7f8bf1645..97937fb67 100644 --- a/requirements/special_requirements.txt +++ b/requirements/special_requirements.txt @@ -2,5 +2,4 @@ # --find-links https://storage.googleapis.com/jax-releases/libtpu_releases.html # --pre -tpu-inference @ git+https://github.com/vllm-project/tpu-inference.git@12eed6e661a1ffacbce9d107a9894c1a471e7479 - +tpu-inference @ git+https://github.com/vllm-project/tpu-inference.git@4a8951606026d5c0307554bc4ed93f4690c4640a