From 279a0efcb49a64cb84b7c70a0aa3bcf901e0d9b2 Mon Sep 17 00:00:00 2001 From: Hongxia Yang <62075498+hongxiayang@users.noreply.github.com> Date: Wed, 25 Sep 2024 10:26:37 -0400 Subject: [PATCH] [CI/Build][Bugfix][Doc][ROCm] CI fix and doc update after ROCm 6.2 upgrade (#8777) --- .buildkite/test-pipeline.yaml | 5 ++++- Dockerfile.rocm | 2 +- docs/source/getting_started/amd-installation.rst | 12 +++++++++++- 3 files changed, 16 insertions(+), 3 deletions(-) diff --git a/.buildkite/test-pipeline.yaml b/.buildkite/test-pipeline.yaml index 379a67c4c8cf8..54dd87bfa2a10 100644 --- a/.buildkite/test-pipeline.yaml +++ b/.buildkite/test-pipeline.yaml @@ -90,8 +90,11 @@ steps: commands: - pip install -e ./plugins/vllm_add_dummy_model - pip install git+https://github.com/EleutherAI/lm-evaluation-harness.git@a4987bba6e9e9b3f22bd3a6c1ecf0abd04fd5622#egg=lm_eval[api] - - pytest -v -s entrypoints/llm --ignore=entrypoints/llm/test_lazy_outlines.py + - pytest -v -s entrypoints/llm --ignore=entrypoints/llm/test_lazy_outlines.py --ignore=entrypoints/llm/test_generate.py --ignore=entrypoints/llm/test_generate_multiple_loras.py --ignore=entrypoints/llm/test_guided_generate.py - pytest -v -s entrypoints/llm/test_lazy_outlines.py # it needs a clean process + - pytest -v -s entrypoints/llm/test_generate.py # it needs a clean process + - pytest -v -s entrypoints/llm/test_generate_multiple_loras.py # it needs a clean process + - pytest -v -s entrypoints/llm/test_guided_generate.py # it needs a clean process - pytest -v -s entrypoints/openai - pytest -v -s entrypoints/test_chat_utils.py - pytest -v -s entrypoints/offline_mode # Needs to avoid interference with other tests diff --git a/Dockerfile.rocm b/Dockerfile.rocm index 9aa3a974e7046..496e6bed7c022 100644 --- a/Dockerfile.rocm +++ b/Dockerfile.rocm @@ -120,7 +120,7 @@ COPY . . # Package upgrades for useful functionality or to avoid dependency issues RUN --mount=type=cache,target=/root/.cache/pip \ - python3 -m pip install --upgrade numba scipy huggingface-hub[cli] + python3 -m pip install --upgrade numba scipy huggingface-hub[cli] pytest-shard # Workaround for ray >= 2.10.0 diff --git a/docs/source/getting_started/amd-installation.rst b/docs/source/getting_started/amd-installation.rst index 4ed0bfe70071d..301337aebcf4c 100644 --- a/docs/source/getting_started/amd-installation.rst +++ b/docs/source/getting_started/amd-installation.rst @@ -28,6 +28,16 @@ Option 1: Build from source with docker (recommended) You can build and install vLLM from source. First, build a docker image from `Dockerfile.rocm `_ and launch a docker container from the image. +It is important that the user kicks off the docker build using buildkit. Either the user put DOCKER_BUILDKIT=1 as environment variable when calling docker build command, or the user needs to setup buildkit in the docker daemon configuration /etc/docker/daemon.json as follows and restart the daemon: + +.. code-block:: console + + { + "features": { + "buildkit": true + } + } + `Dockerfile.rocm `_ uses ROCm 6.2 by default, but also supports ROCm 5.7, 6.0 and 6.1 in older vLLM branches. It provides flexibility to customize the build of docker image using the following arguments: @@ -152,7 +162,7 @@ Note to get your gfx architecture, run `rocminfo |grep gfx`. $ python3 setup.py develop - This may take 5-10 minutes. Currently, `pip install .`` does not work for ROCm installation + This may take 5-10 minutes. Currently, :code:`pip install .` does not work for ROCm installation. .. tip::