From 8ece6956e72b386f096891bc3889c61d6639b3c0 Mon Sep 17 00:00:00 2001 From: Yikun Jiang Date: Sat, 13 Sep 2025 16:21:54 +0800 Subject: [PATCH] Revert "Upgrade CANN version to 8.3.rc1.alpha001 (#2903)" (#2909) ### What this PR does / why we need it? This reverts commit 339fceb89c1571eb8751157bf2d19a9b8479aed0. ### Does this PR introduce _any_ user-facing change? Yes, use 8.2rc1 image by default ### How was this patch tested? CI passed - vLLM version: v0.10.2rc2 - vLLM main: https://github.com/vllm-project/vllm/commit/cfa3234a5b8a6ec4f65ceb080bdc232eaee9b080 Signed-off-by: Yikun Jiang --- .github/workflows/accuracy_test.yaml | 2 +- .github/workflows/nightly_benchmarks.yaml | 2 +- .github/workflows/vllm_ascend_dist.yaml | 2 +- .github/workflows/vllm_ascend_test.yaml | 6 +++--- .github/workflows/vllm_ascend_test_310p.yaml | 2 +- .github/workflows/vllm_ascend_test_full.yaml | 4 ++-- .github/workflows/vllm_ascend_test_pd.yaml | 2 +- Dockerfile | 2 +- Dockerfile.310p | 2 +- Dockerfile.310p.openEuler | 2 +- Dockerfile.a3 | 2 +- Dockerfile.a3.openEuler | 2 +- Dockerfile.openEuler | 2 +- README.md | 2 +- README.zh.md | 2 +- docs/source/conf.py | 2 +- docs/source/installation.md | 2 +- 17 files changed, 20 insertions(+), 20 deletions(-) diff --git a/.github/workflows/accuracy_test.yaml b/.github/workflows/accuracy_test.yaml index 13646da..490a9af 100644 --- a/.github/workflows/accuracy_test.yaml +++ b/.github/workflows/accuracy_test.yaml @@ -76,7 +76,7 @@ jobs: name: ${{ matrix.model_name }} accuracy container: - image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc1.alpha001-910b-ubuntu22.04-py3.11 + image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.2.rc1-910b-ubuntu22.04-py3.11 env: VLLM_USE_MODELSCOPE: True # 1. If version specified (work_dispatch), do specified branch accuracy test diff --git a/.github/workflows/nightly_benchmarks.yaml b/.github/workflows/nightly_benchmarks.yaml index a9a96e1..af35a35 100644 --- a/.github/workflows/nightly_benchmarks.yaml +++ b/.github/workflows/nightly_benchmarks.yaml @@ -56,7 +56,7 @@ jobs: vllm_use_v1: 1 max-parallel: 1 container: - image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc1.alpha001-910b-ubuntu22.04-py3.11 + image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.2.rc1-910b-ubuntu22.04-py3.11 volumes: - /usr/local/dcmi:/usr/local/dcmi - /usr/local/bin/npu-smi:/usr/local/bin/npu-smi diff --git a/.github/workflows/vllm_ascend_dist.yaml b/.github/workflows/vllm_ascend_dist.yaml index c58aac6..b3c91e7 100644 --- a/.github/workflows/vllm_ascend_dist.yaml +++ b/.github/workflows/vllm_ascend_dist.yaml @@ -47,7 +47,7 @@ jobs: name: vLLM Ascend test runs-on: ${{ matrix.os }} container: - image: m.daocloud.io/quay.io/ascend/cann:8.3.rc1.alpha001-a3-ubuntu22.04-py3.11 + image: m.daocloud.io/quay.io/ascend/cann:8.2.rc1-a3-ubuntu22.04-py3.11 env: DEBIAN_FRONTEND: noninteractive steps: diff --git a/.github/workflows/vllm_ascend_test.yaml b/.github/workflows/vllm_ascend_test.yaml index 9936d0a..1e8414a 100644 --- a/.github/workflows/vllm_ascend_test.yaml +++ b/.github/workflows/vllm_ascend_test.yaml @@ -76,7 +76,7 @@ jobs: if: ${{ needs.lint.result == 'success' && (needs.changes.outputs.e2e_tracker == 'true' || needs.changes.outputs.ut_tracker == 'true') }} runs-on: ubuntu-latest container: - image: quay.io/ascend/cann:8.3.rc1.alpha001-910b-ubuntu22.04-py3.11 + image: quay.io/ascend/cann:8.2.rc1-910b-ubuntu22.04-py3.11 env: VLLM_LOGGING_LEVEL: ERROR VLLM_USE_MODELSCOPE: True @@ -142,7 +142,7 @@ jobs: name: singlecard e2e test - light runs-on: ${{ matrix.os }} container: - image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc1.alpha001-910b-ubuntu22.04-py3.11 + image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.2.rc1-910b-ubuntu22.04-py3.11 env: VLLM_LOGGING_LEVEL: ERROR VLLM_USE_MODELSCOPE: True @@ -207,7 +207,7 @@ jobs: name: multicard e2e test - light runs-on: ${{ matrix.os }} container: - image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc1.alpha001-910b-ubuntu22.04-py3.11 + image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.2.rc1-910b-ubuntu22.04-py3.11 env: VLLM_LOGGING_LEVEL: ERROR VLLM_USE_MODELSCOPE: True diff --git a/.github/workflows/vllm_ascend_test_310p.yaml b/.github/workflows/vllm_ascend_test_310p.yaml index a0f4434..cbd472e 100644 --- a/.github/workflows/vllm_ascend_test_310p.yaml +++ b/.github/workflows/vllm_ascend_test_310p.yaml @@ -58,7 +58,7 @@ jobs: runs-on: ${{ matrix.os }} container: # TODO(yikun): Remove m.daocloud.io prefix when infra proxy ready - image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc1.alpha001-310p-ubuntu22.04-py3.11 + image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.2.rc1-310p-ubuntu22.04-py3.11 env: VLLM_LOGGING_LEVEL: ERROR VLLM_USE_MODELSCOPE: True diff --git a/.github/workflows/vllm_ascend_test_full.yaml b/.github/workflows/vllm_ascend_test_full.yaml index 468447b..5694530 100644 --- a/.github/workflows/vllm_ascend_test_full.yaml +++ b/.github/workflows/vllm_ascend_test_full.yaml @@ -76,7 +76,7 @@ jobs: name: singlecard e2e test - full runs-on: ${{ matrix.os }} container: - image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc1.alpha001-910b-ubuntu22.04-py3.11 + image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.2.rc1-910b-ubuntu22.04-py3.11 env: VLLM_LOGGING_LEVEL: ERROR VLLM_USE_MODELSCOPE: True @@ -160,7 +160,7 @@ jobs: name: multicard e2e test - full runs-on: ${{ matrix.os }} container: - image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc1.alpha001-910b-ubuntu22.04-py3.11 + image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.2.rc1-910b-ubuntu22.04-py3.11 env: VLLM_LOGGING_LEVEL: ERROR VLLM_USE_MODELSCOPE: True diff --git a/.github/workflows/vllm_ascend_test_pd.yaml b/.github/workflows/vllm_ascend_test_pd.yaml index 48a34da..fee06be 100644 --- a/.github/workflows/vllm_ascend_test_pd.yaml +++ b/.github/workflows/vllm_ascend_test_pd.yaml @@ -49,7 +49,7 @@ jobs: runs-on: linux-arm64-npu-static-8 container: - image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc1.alpha001-910b-ubuntu22.04-py3.11 + image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.2.rc1-910b-ubuntu22.04-py3.11 volumes: - /usr/local/dcmi:/usr/local/dcmi - /usr/local/bin/npu-smi:/usr/local/bin/npu-smi diff --git a/Dockerfile b/Dockerfile index e5e0d36..ff2bcb3 100644 --- a/Dockerfile +++ b/Dockerfile @@ -15,7 +15,7 @@ # This file is a part of the vllm-ascend project. # -FROM quay.io/ascend/cann:8.3.rc1.alpha001-910b-ubuntu22.04-py3.11 +FROM quay.io/ascend/cann:8.2.rc1-910b-ubuntu22.04-py3.11 ARG PIP_INDEX_URL="https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple" ARG COMPILE_CUSTOM_KERNELS=1 diff --git a/Dockerfile.310p b/Dockerfile.310p index 50c9dbc..366bf33 100644 --- a/Dockerfile.310p +++ b/Dockerfile.310p @@ -15,7 +15,7 @@ # This file is a part of the vllm-ascend project. # -FROM quay.io/ascend/cann:8.3.rc1.alpha001-310p-ubuntu22.04-py3.11 +FROM quay.io/ascend/cann:8.2.rc1-310p-ubuntu22.04-py3.11 ARG PIP_INDEX_URL="https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple" ARG COMPILE_CUSTOM_KERNELS=1 diff --git a/Dockerfile.310p.openEuler b/Dockerfile.310p.openEuler index acbde24..78b1951 100644 --- a/Dockerfile.310p.openEuler +++ b/Dockerfile.310p.openEuler @@ -15,7 +15,7 @@ # This file is a part of the vllm-ascend project. # -FROM quay.io/ascend/cann:8.3.rc1.alpha001-310p-openeuler22.03-py3.11 +FROM quay.io/ascend/cann:8.2.rc1-310p-openeuler24.03-py3.11 ARG PIP_INDEX_URL="https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple" ARG COMPILE_CUSTOM_KERNELS=1 diff --git a/Dockerfile.a3 b/Dockerfile.a3 index 3499197..40bf51b 100644 --- a/Dockerfile.a3 +++ b/Dockerfile.a3 @@ -15,7 +15,7 @@ # This file is a part of the vllm-ascend project. # -FROM quay.io/ascend/cann:8.3.rc1.alpha001-a3-ubuntu22.04-py3.11 +FROM quay.io/ascend/cann:8.2.rc1-a3-ubuntu22.04-py3.11 ARG PIP_INDEX_URL="https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple" ARG COMPILE_CUSTOM_KERNELS=1 diff --git a/Dockerfile.a3.openEuler b/Dockerfile.a3.openEuler index 04fc604..f462522 100644 --- a/Dockerfile.a3.openEuler +++ b/Dockerfile.a3.openEuler @@ -15,7 +15,7 @@ # This file is a part of the vllm-ascend project. # -FROM quay.io/ascend/cann:8.3.rc1.alpha001-a3-openeuler22.03-py3.11 +FROM quay.io/ascend/cann:8.2.rc1-a3-openeuler24.03-py3.11 ARG PIP_INDEX_URL="https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple" ARG COMPILE_CUSTOM_KERNELS=1 diff --git a/Dockerfile.openEuler b/Dockerfile.openEuler index 99f777a..2c0ee86 100644 --- a/Dockerfile.openEuler +++ b/Dockerfile.openEuler @@ -15,7 +15,7 @@ # This file is a part of the vllm-ascend project. # -FROM quay.io/ascend/cann:8.3.rc1.alpha001-910b-openeuler22.03-py3.11 +FROM quay.io/ascend/cann:8.2.rc1-910b-openeuler24.03-py3.11 ARG PIP_INDEX_URL="https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple" ARG COMPILE_CUSTOM_KERNELS=1 diff --git a/README.md b/README.md index 0bf6275..d766cc4 100644 --- a/README.md +++ b/README.md @@ -42,7 +42,7 @@ By using vLLM Ascend plugin, popular open-source models, including Transformer-l - OS: Linux - Software: * Python >= 3.9, < 3.12 - * CANN >= 8.3.rc1.alpha001 (Ascend HDK version refers to [here](https://www.hiascend.com/document/detail/zh/canncommercial/82RC1/releasenote/releasenote_0000.html)) + * CANN >= 8.2.rc1 (Ascend HDK version refers to [here](https://www.hiascend.com/document/detail/zh/canncommercial/82RC1/releasenote/releasenote_0000.html)) * PyTorch >= 2.7.1, torch-npu >= 2.7.1.dev20250724 * vLLM (the same version as vllm-ascend) diff --git a/README.zh.md b/README.zh.md index 99689eb..d31a0f3 100644 --- a/README.zh.md +++ b/README.zh.md @@ -43,7 +43,7 @@ vLLM 昇腾插件 (`vllm-ascend`) 是一个由社区维护的让vLLM在Ascend NP - 操作系统：Linux - 软件： * Python >= 3.9, < 3.12 - * CANN >= 8.3.rc1.alpha001 (Ascend HDK 版本参考[这里](https://www.hiascend.com/document/detail/zh/canncommercial/82RC1/releasenote/releasenote_0000.html)) + * CANN >= 8.2.rc1 (Ascend HDK 版本参考[这里](https://www.hiascend.com/document/detail/zh/canncommercial/82RC1/releasenote/releasenote_0000.html)) * PyTorch >= 2.7.1, torch-npu >= 2.7.1.dev20250724 * vLLM (与vllm-ascend版本一致) diff --git a/docs/source/conf.py b/docs/source/conf.py index 70f45cd..98eaa46 100644 --- a/docs/source/conf.py +++ b/docs/source/conf.py @@ -75,7 +75,7 @@ myst_substitutions = { 'pip_vllm_ascend_version': "0.10.1rc1", 'pip_vllm_version': "0.10.1.1", # CANN image tag - 'cann_image_tag': "8.3.rc1.alpha001-910b-ubuntu22.04-py3.11", + 'cann_image_tag': "8.2.rc1-910b-ubuntu22.04-py3.11", # vllm version in ci 'ci_vllm_version': 'v0.10.2rc2', } diff --git a/docs/source/installation.md b/docs/source/installation.md index 1f02506..0d3b54d 100644 --- a/docs/source/installation.md +++ b/docs/source/installation.md @@ -12,7 +12,7 @@ This document describes how to install vllm-ascend manually. | Software | Supported version | Note | |---------------|----------------------------------|-------------------------------------------| | Ascend HDK | Refer to [here](https://www.hiascend.com/document/detail/zh/canncommercial/82RC1/releasenote/releasenote_0000.html) | Required for CANN | - | CANN | >= 8.3.rc1.alpha001 | Required for vllm-ascend and torch-npu | + | CANN | >= 8.2.RC1 | Required for vllm-ascend and torch-npu | | torch-npu | >= 2.7.1.dev20250724 | Required for vllm-ascend, No need to install manually, it will be auto installed in below steps | | torch | >= 2.7.1 | Required for torch-npu and vllm |