From a7f48927098a5e392e50aa310b8428a864ab4880 Mon Sep 17 00:00:00 2001 From: aoshen02 Date: Fri, 4 Sep 2026 08:32:48 +0000 Subject: [PATCH] ci: allow candidate image selection Signed-off-by: aoshen02 --- .buildkite/README.md | 10 +++++----- .buildkite/gpu_suites.py | 2 +- .buildkite/pipeline.yml | 2 +- docs/en/developer_guide/ci.md | 5 +++-- docs/zh/developer_guide/ci.md | 4 ++-- 5 files changed, 12 insertions(+), 11 deletions(-) diff --git a/.buildkite/README.md b/.buildkite/README.md index 5449bcbdd..11876bf03 100644 --- a/.buildkite/README.md +++ b/.buildkite/README.md @@ -17,9 +17,9 @@ The four test steps depend on the pre-commit gate. Each suite runs its files sequentially inside one step because these queues boot a fresh EC2 instance per job — a per-file matrix would be mostly boot + pip-install time. Most always-on CPU steps use the standard `python:3.11` image and install their -lightweight dependencies at runtime. `upstream-sync-cpu` uses -`vllm/vime:latest` because the synchronized GLM and checkpoint tests import the -image-pinned Megatron stack even though they do not allocate a GPU. +lightweight dependencies at runtime. `upstream-sync-cpu` uses `VIME_CI_IMAGE` +(defaulting to `vllm/vime:latest`) because the synchronized GLM and checkpoint +tests import the image-pinned Megatron stack even though they do not allocate a GPU. ## Creating the pipeline (one-time, Buildkite UI) @@ -70,8 +70,8 @@ startup, so a warm HF cache is all they need. `WANDB_API_KEY` is not wired up yet; runs report without wandb until it's added (e.g. as a k8s secret in the pod spec). -GPU jobs use `vllm/vime:latest`. Rebuild and publish that image before validating -Dockerfile or vLLM patch changes. +Set `VIME_CI_IMAGE` to an immutable candidate digest for image-backed jobs; +otherwise they use `vllm/vime:latest`. Do not update `latest` before merge. ## Keeping it in sync diff --git a/.buildkite/gpu_suites.py b/.buildkite/gpu_suites.py index 0aec7c898..243bc22f8 100644 --- a/.buildkite/gpu_suites.py +++ b/.buildkite/gpu_suites.py @@ -23,7 +23,7 @@ import subprocess GPU_QUEUE = "mithril-h100-pool" -CI_IMAGE = "vllm/vime:latest" +CI_IMAGE = os.environ.get("VIME_CI_IMAGE", "vllm/vime:latest") HF_CACHE_HOST_PATH = "/mnt/hf-cache" HF_HOME = "/root/.cache/huggingface" NODE_INSTANCE_TYPE = "gpu-h100-sxm" diff --git a/.buildkite/pipeline.yml b/.buildkite/pipeline.yml index ec22ecfe9..dbc8b2258 100644 --- a/.buildkite/pipeline.yml +++ b/.buildkite/pipeline.yml @@ -140,7 +140,7 @@ steps: -e GIT_CONFIG_PARAMETERS="'safe.directory=/workspace'" \ -e GLOO_SOCKET_IFNAME=lo -e TP_SOCKET_IFNAME=lo \ -v "$$PWD:/workspace" -w /workspace \ - vllm/vime:latest bash -lc ' + "$${VIME_CI_IMAGE:-vllm/vime:latest}" bash -lc ' set -euo pipefail pip install -q -e . --no-deps --break-system-packages for test_file in \ diff --git a/docs/en/developer_guide/ci.md b/docs/en/developer_guide/ci.md index 738403f5e..0d40b3083 100644 --- a/docs/en/developer_guide/ci.md +++ b/docs/en/developer_guide/ci.md @@ -31,8 +31,9 @@ After the CPU steps pass, the Buildkite build exposes a block step named - `ckpt` `.buildkite/gpu_suites.py` expands each selected suite into one Buildkite job -per test. GPU tests use `vllm/vime:latest`; rebuild and publish that image -before validating a Dockerfile or vLLM patch change. +per test. Set `VIME_CI_IMAGE` to an immutable candidate digest when validating +Dockerfile or vLLM patch changes. Jobs otherwise use `vllm/vime:latest`, which +must not be updated before the change merges. ## Registering tests diff --git a/docs/zh/developer_guide/ci.md b/docs/zh/developer_guide/ci.md index 0fa353287..5fbd123fb 100644 --- a/docs/zh/developer_guide/ci.md +++ b/docs/zh/developer_guide/ci.md @@ -30,8 +30,8 @@ block step。可以选择一个或多个套件： - `ckpt` `.buildkite/gpu_suites.py` 会把所选套件展开为每个测试一个 Buildkite -job。GPU 测试使用 `vllm/vime:latest`；验证 Dockerfile 或 vLLM patch 修改前， -需要先重建并发布该镜像。 +job。验证 Dockerfile 或 vLLM patch 修改时，通过 `VIME_CI_IMAGE` 指定不可变的 +候选镜像 digest；未设置时使用 `vllm/vime:latest`，且 PR 合入前不得更新该标签。 ## 注册测试