From f61c0639ac7116f21ab642cc8d882a1661367e43 Mon Sep 17 00:00:00 2001 From: youkaichao Date: Mon, 16 Dec 2024 16:01:33 -0800 Subject: [PATCH] typo fix Signed-off-by: youkaichao --- .buildkite/run-gh200-test.sh | 2 +- docs/source/serving/deploying_with_docker.rst | 5 +---- 2 files changed, 2 insertions(+), 5 deletions(-) diff --git a/.buildkite/run-gh200-test.sh b/.buildkite/run-gh200-test.sh index d25510c47fe6b..875e737cd856c 100644 --- a/.buildkite/run-gh200-test.sh +++ b/.buildkite/run-gh200-test.sh @@ -7,7 +7,7 @@ set -ex # Try building the docker image DOCKER_BUILDKIT=1 docker build . \ --target test \ - -platform "linux/arm64" \ + --platform "linux/arm64" \ -t gh200-test \ --build-arg max_jobs=66 \ --build-arg nvcc_threads=2 \ diff --git a/docs/source/serving/deploying_with_docker.rst b/docs/source/serving/deploying_with_docker.rst index 11a9f12fd17cd..56f0020a1011a 100644 --- a/docs/source/serving/deploying_with_docker.rst +++ b/docs/source/serving/deploying_with_docker.rst @@ -54,16 +54,13 @@ of PyTorch Nightly and should be considered **experimental**. Using the flag `-- # Example of building on Nvidia GH200 server. (Memory usage: ~12GB, Build time: ~1475s / ~25 min, Image size: 7.26GB) $ DOCKER_BUILDKIT=1 sudo docker build . \ --target vllm-openai \ - -platform "linux/arm64" \ + --platform "linux/arm64" \ -t vllm/vllm-gh200-openai:latest \ --build-arg max_jobs=66 \ --build-arg nvcc_threads=2 \ --build-arg torch_cuda_arch_list="9.0+PTX" \ --build-arg vllm_fa_cmake_gpu_arches="90-real" - - - To run vLLM: .. code-block:: console