diff --git a/.github/workflows/bot_pr_create.yaml b/.github/workflows/bot_pr_create.yaml index 235d0c7d..b4228a21 100644 --- a/.github/workflows/bot_pr_create.yaml +++ b/.github/workflows/bot_pr_create.yaml @@ -37,7 +37,7 @@ jobs: steps: - name: Get vLLM version run: | - VLLM_COMMIT=ed359c497a728f08b5b41456c07a688ccd510fbc + VLLM_COMMIT=v0.18.0 echo "VLLM_COMMIT=https://github.com/vllm-project/vllm/commit/$VLLM_COMMIT" >> "$GITHUB_ENV" - name: Checkout repository diff --git a/.github/workflows/dockerfiles/Dockerfile.lint b/.github/workflows/dockerfiles/Dockerfile.lint index 26e4631c..02eea498 100644 --- a/.github/workflows/dockerfiles/Dockerfile.lint +++ b/.github/workflows/dockerfiles/Dockerfile.lint @@ -27,7 +27,7 @@ RUN apt-get update -y && \ ARG VLLM_REPO=https://github.com/vllm-project/vllm.git # For lint purpose, actually we need make a main2main matching. -ARG VLLM_COMMIT=ed359c497a728f08b5b41456c07a688ccd510fbc +ARG VLLM_COMMIT=v0.18.0 RUN git clone $VLLM_REPO /vllm-workspace/vllm && \ cd /vllm-workspace/vllm && \ git checkout $VLLM_COMMIT diff --git a/.github/workflows/dockerfiles/Dockerfile.nightly.a2 b/.github/workflows/dockerfiles/Dockerfile.nightly.a2 index bd990761..0cdb1ce1 100644 --- a/.github/workflows/dockerfiles/Dockerfile.nightly.a2 +++ b/.github/workflows/dockerfiles/Dockerfile.nightly.a2 @@ -15,7 +15,7 @@ # This file is a part of the vllm-ascend project. # -FROM quay.io/ascend/vllm-ascend:main +FROM quay.io/ascend/vllm-ascend:release-0.18.0 ARG PIP_INDEX_URL="https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple" ARG AIS_BENCH_TAG="v3.0-20250930-master" diff --git a/.github/workflows/dockerfiles/Dockerfile.nightly.a3 b/.github/workflows/dockerfiles/Dockerfile.nightly.a3 index 176eeb57..8436c0f2 100644 --- a/.github/workflows/dockerfiles/Dockerfile.nightly.a3 +++ b/.github/workflows/dockerfiles/Dockerfile.nightly.a3 @@ -15,7 +15,7 @@ # This file is a part of the vllm-ascend project. # -FROM quay.io/ascend/vllm-ascend:main-a3 +FROM quay.io/ascend/vllm-ascend:releases-v0.18.0-a3 ARG PIP_INDEX_URL="https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple" ARG AIS_BENCH_TAG="v3.0-20250930-master" diff --git a/.github/workflows/pr_test_full.yaml b/.github/workflows/pr_test_full.yaml index 2ad78980..440af461 100644 --- a/.github/workflows/pr_test_full.yaml +++ b/.github/workflows/pr_test_full.yaml @@ -75,7 +75,7 @@ jobs: name: e2e-full strategy: matrix: - vllm_version: [ed359c497a728f08b5b41456c07a688ccd510fbc, v0.18.0] + vllm_version: [v0.18.0] needs: [changes] if: ${{ needs.changes.outputs.e2e_tracker == 'true' || needs.changes.outputs.e2e_tracker == true }} uses: ./.github/workflows/_e2e_test.yaml diff --git a/.github/workflows/pr_test_light.yaml b/.github/workflows/pr_test_light.yaml index 6bdf2425..1139df36 100644 --- a/.github/workflows/pr_test_light.yaml +++ b/.github/workflows/pr_test_light.yaml @@ -41,7 +41,7 @@ jobs: lint: uses: ./.github/workflows/_pre_commit.yml with: - vllm: ed359c497a728f08b5b41456c07a688ccd510fbc + vllm: v0.18.0 changes: runs-on: linux-aarch64-a2b3-0 outputs: @@ -90,7 +90,7 @@ jobs: if: ${{ needs.lint.result == 'success' && (needs.changes.outputs.e2e_tracker == 'true' || needs.changes.outputs.ut_tracker == 'true') }} strategy: matrix: - vllm_version: [ed359c497a728f08b5b41456c07a688ccd510fbc, v0.18.0] + vllm_version: [v0.18.0] uses: ./.github/workflows/_unit_test.yaml with: vllm: ${{ matrix.vllm_version }} @@ -102,7 +102,7 @@ jobs: name: e2e-light strategy: matrix: - vllm_version: [ed359c497a728f08b5b41456c07a688ccd510fbc, v0.18.0] + vllm_version: [v0.18.0] # Note (yikun): If CI resource are limited we can split job into two chain jobs needs: [lint, changes] # only trigger e2e test after lint passed and the change is e2e related with pull request. diff --git a/.github/workflows/schedule_codecov_refresh.yaml b/.github/workflows/schedule_codecov_refresh.yaml index 83ddaf97..12b20861 100644 --- a/.github/workflows/schedule_codecov_refresh.yaml +++ b/.github/workflows/schedule_codecov_refresh.yaml @@ -33,7 +33,7 @@ jobs: name: refresh codecov strategy: matrix: - vllm_version: [ed359c497a728f08b5b41456c07a688ccd510fbc] + vllm_version: [v0.18.0] uses: ./.github/workflows/_unit_test.yaml with: vllm: ${{ matrix.vllm_version }} diff --git a/docs/source/community/versioning_policy.md b/docs/source/community/versioning_policy.md index 24ada475..315b7911 100644 --- a/docs/source/community/versioning_policy.md +++ b/docs/source/community/versioning_policy.md @@ -59,7 +59,7 @@ For main branch of vLLM Ascend, we usually make it compatible with the latest vL | vLLM Ascend | vLLM | Python | Stable CANN | PyTorch/torch_npu | |-------------|--------------|------------------|-------------|--------------------| -| main | ed359c497a728f08b5b41456c07a688ccd510fbc, v0.18.0 tag | >= 3.10, < 3.12 | 8.5.0 | 2.9.0 / 2.9.0 | +| main | v0.18.0 tag | >= 3.10, < 3.12 | 8.5.0 | 2.9.0 / 2.9.0 | ## Release cadence diff --git a/vllm_ascend/worker/v2/README.md b/vllm_ascend/worker/v2/README.md index 2e2fd232..4ed68f5b 100644 --- a/vllm_ascend/worker/v2/README.md +++ b/vllm_ascend/worker/v2/README.md @@ -5,5 +5,5 @@ This directory contains the new model runner which is under active development. please see [Model Runner V2](https://github.com/vllm-project/vllm-ascend/issues/5208) to get specific plans. -supported vllm version: main@ed359c497a728f08b5b41456c07a688ccd510fbc +supported vllm version: v0.18.0 related PR: