FilesExpand file tree

 main

/

test-wheel-linux.yml

Copy path

View Runs

Blame

More file actions

Blame

More file actions

Latest commit

 

History

History

History

332 lines (295 loc) · 14.9 KB

 main

/

test-wheel-linux.yml

Copy path

Top

File metadata and controls

• Code
• Blame

332 lines (295 loc) · 14.9 KB

Raw

Copy raw file

Download raw file

Open symbols panel

Edit and raw actions

1

2

3

4

5

6

7

8

9

10

11

12

13

14

15

16

17

18

19

20

21

22

23

24

25

26

27

28

29

30

31

32

33

34

35

36

37

38

39

40

41

42

43

44

45

46

47

48

49

50

51

52

53

54

55

56

57

58

59

60

61

62

63

64

65

66

67

68

69

70

71

72

73

74

75

76

77

78

79

80

81

82

83

84

85

86

87

88

89

90

91

92

93

94

95

96

97

98

99

100

101

102

103

104

105

106

107

108

109

110

111

112

113

114

115

116

117

118

119

120

121

122

123

124

125

126

127

128

129

130

131

132

133

134

135

136

137

138

139

140

141

142

143

144

145

146

147

148

149

150

151

152

153

154

155

156

157

158

159

160

161

162

163

164

165

166

167

168

169

170

171

172

173

174

175

176

177

178

179

180

181

182

183

184

185

186

187

188

189

190

191

192

193

194

195

196

197

198

199

200

201

202

203

204

205

206

207

208

209

210

211

212

213

214

215

216

217

218

219

220

221

222

223

224

225

226

227

228

229

230

231

232

233

234

235

236

237

238

239

240

241

242

243

244

245

246

247

248

249

250

251

252

253

254

255

256

257

258

259

260

261

262

263

264

265

266

267

268

269

270

271

272

273

274

275

276

277

278

279

280

281

282

283

284

285

286

287

288

289

290

291

292

293

294

295

296

297

298

299

300

301

302

303

304

305

306

307

308

309

310

311

312

313

314

315

316

317

318

319

320

321

322

323

324

325

326

327

328

329

330

331

332

# SPDX-FileCopyrightText: Copyright (c) 2024-2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.

#

# SPDX-License-Identifier: Apache-2.0

name: "CI: Test wheels"

on:

workflow_call:

inputs:

build-type:

type: string

required: true

host-platform:

type: string

required: true

build-ctk-ver:

type: string

required: true

matrix_filter:

type: string

default: "."

defaults:

run:

shell: bash --noprofile --norc -xeuo pipefail {0}

jobs:

compute-matrix:

runs-on: ubuntu-latest

env:

BUILD_TYPE: ${{ inputs.build-type }}

ARCH: ${{ (inputs.host-platform == 'linux-64' && 'amd64') ||

(inputs.host-platform == 'linux-aarch64' && 'arm64') }}

outputs:

MATRIX: ${{ steps.compute-matrix.outputs.MATRIX }}

steps:

- name: Validate Test Type

run: |

if [[ "$BUILD_TYPE" != "pull-request" ]] && [[ "$BUILD_TYPE" != "nightly" ]] && [[ "$BUILD_TYPE" != "branch" ]]; then

echo "Invalid build type! Must be one of 'nightly', 'pull-request', or 'branch'."

exit 1

fi

- name: Compute Python Test Matrix

id: compute-matrix

run: |

# Set a default GPU based upon architecture.

gpu="l4"

if [[ "${ARCH}" == "arm64" ]]; then

gpu="a100"

fi

# Add a special entry for the H100 runner on amd64.

special_runner=""

if [[ "${ARCH}" == "amd64" ]]; then

special_runner="- { ARCH: ${ARCH}, PY_VER: '3.13', CUDA_VER: '13.0.0', LOCAL_CTK: '1', GPU: 'H100', DRIVER: 'latest' }"

fi

# Please keep the matrices sorted in ascending order by the following:

#

# [PY_VER, CUDA_VER, LOCAL_CTK, GPU, DRIVER]

#

# Note that DRIVER: `earliest` does not work with CUDA 12.9.0 and LOCAL_CTK: 0 does not work with CUDA 12.0.1.

#

export MATRICES="

pull-request:

- { ARCH: ${ARCH}, PY_VER: '3.9', CUDA_VER: '12.9.0', LOCAL_CTK: '0', GPU: ${gpu}, DRIVER: 'latest' }

- { ARCH: ${ARCH}, PY_VER: '3.9', CUDA_VER: '13.0.0', LOCAL_CTK: '1', GPU: ${gpu}, DRIVER: 'latest' }

- { ARCH: ${ARCH}, PY_VER: '3.10', CUDA_VER: '12.9.0', LOCAL_CTK: '1', GPU: ${gpu}, DRIVER: 'latest' }

- { ARCH: ${ARCH}, PY_VER: '3.10', CUDA_VER: '13.0.0', LOCAL_CTK: '0', GPU: ${gpu}, DRIVER: 'latest' }

- { ARCH: ${ARCH}, PY_VER: '3.11', CUDA_VER: '12.9.0', LOCAL_CTK: '0', GPU: ${gpu}, DRIVER: 'latest' }

- { ARCH: ${ARCH}, PY_VER: '3.11', CUDA_VER: '13.0.0', LOCAL_CTK: '1', GPU: ${gpu}, DRIVER: 'latest' }

- { ARCH: ${ARCH}, PY_VER: '3.12', CUDA_VER: '12.9.0', LOCAL_CTK: '1', GPU: ${gpu}, DRIVER: 'latest' }

- { ARCH: ${ARCH}, PY_VER: '3.12', CUDA_VER: '13.0.0', LOCAL_CTK: '0', GPU: ${gpu}, DRIVER: 'latest' }

- { ARCH: ${ARCH}, PY_VER: '3.13', CUDA_VER: '12.9.0', LOCAL_CTK: '0', GPU: ${gpu}, DRIVER: 'latest' }

- { ARCH: ${ARCH}, PY_VER: '3.13', CUDA_VER: '13.0.0', LOCAL_CTK: '1', GPU: ${gpu}, DRIVER: 'latest' }

${special_runner}

nightly:

- { ARCH: ${ARCH}, PY_VER: '3.9', CUDA_VER: '11.8.0', LOCAL_CTK: '0', GPU: ${gpu}, DRIVER: 'earliest' }

- { ARCH: ${ARCH}, PY_VER: '3.9', CUDA_VER: '11.8.0', LOCAL_CTK: '1', GPU: ${gpu}, DRIVER: 'latest' }

- { ARCH: ${ARCH}, PY_VER: '3.9', CUDA_VER: '12.0.1', LOCAL_CTK: '1', GPU: ${gpu}, DRIVER: 'latest' }

- { ARCH: ${ARCH}, PY_VER: '3.9', CUDA_VER: '12.9.0', LOCAL_CTK: '0', GPU: ${gpu}, DRIVER: 'latest' }

- { ARCH: ${ARCH}, PY_VER: '3.9', CUDA_VER: '12.9.0', LOCAL_CTK: '1', GPU: ${gpu}, DRIVER: 'latest' }

- { ARCH: ${ARCH}, PY_VER: '3.10', CUDA_VER: '11.8.0', LOCAL_CTK: '0', GPU: ${gpu}, DRIVER: 'earliest' }

- { ARCH: ${ARCH}, PY_VER: '3.10', CUDA_VER: '11.8.0', LOCAL_CTK: '1', GPU: ${gpu}, DRIVER: 'latest' }

- { ARCH: ${ARCH}, PY_VER: '3.10', CUDA_VER: '12.0.1', LOCAL_CTK: '1', GPU: ${gpu}, DRIVER: 'latest' }

- { ARCH: ${ARCH}, PY_VER: '3.10', CUDA_VER: '12.9.0', LOCAL_CTK: '0', GPU: ${gpu}, DRIVER: 'latest' }

- { ARCH: ${ARCH}, PY_VER: '3.10', CUDA_VER: '12.9.0', LOCAL_CTK: '1', GPU: ${gpu}, DRIVER: 'latest' }

- { ARCH: ${ARCH}, PY_VER: '3.11', CUDA_VER: '11.8.0', LOCAL_CTK: '0', GPU: ${gpu}, DRIVER: 'earliest' }

- { ARCH: ${ARCH}, PY_VER: '3.11', CUDA_VER: '11.8.0', LOCAL_CTK: '1', GPU: ${gpu}, DRIVER: 'latest' }

- { ARCH: ${ARCH}, PY_VER: '3.11', CUDA_VER: '12.0.1', LOCAL_CTK: '1', GPU: ${gpu}, DRIVER: 'latest' }

- { ARCH: ${ARCH}, PY_VER: '3.11', CUDA_VER: '12.9.0', LOCAL_CTK: '0', GPU: ${gpu}, DRIVER: 'latest' }

- { ARCH: ${ARCH}, PY_VER: '3.11', CUDA_VER: '12.9.0', LOCAL_CTK: '1', GPU: ${gpu}, DRIVER: 'latest' }

- { ARCH: ${ARCH}, PY_VER: '3.12', CUDA_VER: '11.8.0', LOCAL_CTK: '0', GPU: ${gpu}, DRIVER: 'earliest' }

- { ARCH: ${ARCH}, PY_VER: '3.12', CUDA_VER: '11.8.0', LOCAL_CTK: '1', GPU: ${gpu}, DRIVER: 'latest' }

- { ARCH: ${ARCH}, PY_VER: '3.12', CUDA_VER: '12.0.1', LOCAL_CTK: '1', GPU: ${gpu}, DRIVER: 'latest' }

- { ARCH: ${ARCH}, PY_VER: '3.12', CUDA_VER: '12.9.0', LOCAL_CTK: '0', GPU: ${gpu}, DRIVER: 'latest' }

- { ARCH: ${ARCH}, PY_VER: '3.12', CUDA_VER: '12.9.0', LOCAL_CTK: '1', GPU: ${gpu}, DRIVER: 'latest' }

- { ARCH: ${ARCH}, PY_VER: '3.13', CUDA_VER: '11.8.0', LOCAL_CTK: '0', GPU: ${gpu}, DRIVER: 'earliest' }

- { ARCH: ${ARCH}, PY_VER: '3.13', CUDA_VER: '11.8.0', LOCAL_CTK: '1', GPU: ${gpu}, DRIVER: 'latest' }

- { ARCH: ${ARCH}, PY_VER: '3.13', CUDA_VER: '12.0.1', LOCAL_CTK: '1', GPU: ${gpu}, DRIVER: 'latest' }

- { ARCH: ${ARCH}, PY_VER: '3.13', CUDA_VER: '12.9.0', LOCAL_CTK: '0', GPU: ${gpu}, DRIVER: 'latest' }

- { ARCH: ${ARCH}, PY_VER: '3.13', CUDA_VER: '12.9.0', LOCAL_CTK: '1', GPU: ${gpu}, DRIVER: 'latest' }

${special_runner}

"

# Use the nightly matrix for branch tests

MATRIX_TYPE="${BUILD_TYPE}"

if [[ "${MATRIX_TYPE}" == "branch" ]]; then

MATRIX_TYPE="nightly"

fi

export MATRIX_TYPE

TEST_MATRIX=$(yq -n 'env(MATRICES) | .[strenv(MATRIX_TYPE)]')

export TEST_MATRIX

MATRIX="$(

yq -n -o json 'env(TEST_MATRIX)' | \

jq -c '${{ inputs.matrix_filter }} | if (. | length) > 0 then {include: .} else "Error: Empty matrix\n" | halt_error(1) end'

)"

echo "MATRIX=${MATRIX}" | tee --append "${GITHUB_OUTPUT}"

test:

name: py${{ matrix.PY_VER }}, ${{ matrix.CUDA_VER }}, ${{ (matrix.LOCAL_CTK == '1' && 'local') || 'wheels' }}, GPU ${{ matrix.GPU }}

needs: compute-matrix

strategy:

fail-fast: false

matrix: ${{ fromJSON(needs.compute-matrix.outputs.MATRIX) }}

runs-on: "linux-${{ matrix.ARCH }}-gpu-${{ matrix.GPU }}-${{ matrix.DRIVER }}-1"

# The build stage could fail but we want the CI to keep moving.

if: ${{ github.repository_owner == 'nvidia' && !cancelled() }}

# Our self-hosted runners require a container

# TODO: use a different (nvidia?) container

container:

options: -u root --security-opt seccomp=unconfined --shm-size 16g

image: ubuntu:22.04

env:

NVIDIA_VISIBLE_DEVICES: ${{ env.NVIDIA_VISIBLE_DEVICES }}

steps:

- name: Ensure GPU is working

run: nvidia-smi

- name: Checkout ${{ github.event.repository.name }}

uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5.0.0

with:

fetch-depth: 0

- name: Install dependencies

uses: ./.github/actions/install_unix_deps

continue-on-error: false

with:

# for artifact fetching

dependencies: "jq wget"

dependent_exes: "jq wget"

- name: Set environment variables

env:

BUILD_CUDA_VER: ${{ inputs.build-ctk-ver }}

CUDA_VER: ${{ matrix.CUDA_VER }}

HOST_PLATFORM: ${{ inputs.host-platform }}

LOCAL_CTK: ${{ matrix.LOCAL_CTK }}

PY_VER: ${{ matrix.PY_VER }}

SHA: ${{ github.sha }}

run: ./ci/tools/env-vars test

- name: Download cuda-pathfinder build artifacts

uses: actions/download-artifact@634f93cb2916e3fdff6788551b99b062d0335ce0 # v5.0.0

with:

name: cuda-pathfinder-wheel

path: ./cuda_pathfinder

- name: Download cuda-python build artifacts

if: ${{ env.SKIP_CUDA_BINDINGS_TEST == '0'}}

uses: actions/download-artifact@634f93cb2916e3fdff6788551b99b062d0335ce0 # v5.0.0

with:

name: cuda-python-wheel

path: .

- name: Download cuda.bindings build artifacts

if: ${{ env.SKIP_CUDA_BINDINGS_TEST == '0'}}

uses: actions/download-artifact@634f93cb2916e3fdff6788551b99b062d0335ce0 # v5.0.0

with:

name: ${{ env.CUDA_BINDINGS_ARTIFACT_NAME }}

path: ${{ env.CUDA_BINDINGS_ARTIFACTS_DIR }}

- name: Download cuda-python & cuda.bindings build artifacts from the prior branch

if: ${{ env.SKIP_CUDA_BINDINGS_TEST == '1'}}

env:

GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}

run: |

# See https://github.com/cli/cli/blob/trunk/docs/install_linux.md#debian-ubuntu-linux-raspberry-pi-os-apt.

# gh is needed for artifact fetching.

mkdir -p -m 755 /etc/apt/keyrings \

&& out=$(mktemp) && wget -nv -O$out https://cli.github.com/packages/githubcli-archive-keyring.gpg \

&& cat $out | tee /etc/apt/keyrings/githubcli-archive-keyring.gpg > /dev/null \

&& chmod go+r /etc/apt/keyrings/githubcli-archive-keyring.gpg \

&& echo "deb [arch=$(dpkg --print-architecture) signed-by=/etc/apt/keyrings/githubcli-archive-keyring.gpg] https://cli.github.com/packages stable main" | tee /etc/apt/sources.list.d/github-cli.list > /dev/null \

&& apt update \

&& apt install gh -y

OLD_BRANCH=$(cat .github/BACKPORT_BRANCH)

OLD_BASENAME="cuda-bindings-python${PYTHON_VERSION_FORMATTED}-cuda*-${{ inputs.host-platform }}*"

LATEST_PRIOR_RUN_ID=$(gh run list -b ${OLD_BRANCH} -L 1 -w "ci.yml" -s completed -R NVIDIA/cuda-python --json databaseId | jq '.[]| .databaseId')

if [[ "$LATEST_PRIOR_RUN_ID" == "" ]]; then

echo "LATEST_PRIOR_RUN_ID not found!"

exit 1

fi

gh run download $LATEST_PRIOR_RUN_ID -p ${OLD_BASENAME} -R NVIDIA/cuda-python

rm -rf ${OLD_BASENAME}-tests # exclude cython test artifacts

ls -al $OLD_BASENAME

mkdir -p "${{ env.CUDA_BINDINGS_ARTIFACTS_DIR }}"

mv $OLD_BASENAME/*.whl "${{ env.CUDA_BINDINGS_ARTIFACTS_DIR }}"/

rmdir $OLD_BASENAME

gh run download $LATEST_PRIOR_RUN_ID -p cuda-python-wheel -R NVIDIA/cuda-python

ls -al cuda-python-wheel

mv cuda-python-wheel/*.whl .

rmdir cuda-python-wheel

- name: Display structure of downloaded cuda-python artifacts

run: |

pwd

ls -lahR .

- name: Display structure of downloaded cuda.bindings artifacts

run: |

pwd

ls -lahR $CUDA_BINDINGS_ARTIFACTS_DIR

- name: Download cuda.bindings Cython tests

if: ${{ env.SKIP_CYTHON_TEST == '0' }}

uses: actions/download-artifact@634f93cb2916e3fdff6788551b99b062d0335ce0 # v5.0.0

with:

name: ${{ env.CUDA_BINDINGS_ARTIFACT_NAME }}-tests

path: ${{ env.CUDA_BINDINGS_CYTHON_TESTS_DIR }}

- name: Display structure of downloaded cuda.bindings Cython tests

if: ${{ env.SKIP_CYTHON_TEST == '0' }}

run: |

pwd

ls -lahR $CUDA_BINDINGS_CYTHON_TESTS_DIR

- name: Download cuda.core build artifacts

uses: actions/download-artifact@634f93cb2916e3fdff6788551b99b062d0335ce0 # v5.0.0

with:

name: ${{ env.CUDA_CORE_ARTIFACT_NAME }}

path: ${{ env.CUDA_CORE_ARTIFACTS_DIR }}

- name: Display structure of downloaded cuda.core build artifacts

run: |

pwd

ls -lahR $CUDA_CORE_ARTIFACTS_DIR

- name: Download cuda.core Cython tests

if: ${{ env.SKIP_CYTHON_TEST == '0' }}

uses: actions/download-artifact@634f93cb2916e3fdff6788551b99b062d0335ce0 # v5.0.0

with:

name: ${{ env.CUDA_CORE_ARTIFACT_NAME }}-tests

path: ${{ env.CUDA_CORE_CYTHON_TESTS_DIR }}

- name: Display structure of downloaded cuda.core Cython tests

if: ${{ env.SKIP_CYTHON_TEST == '0' }}

run: |

pwd

ls -lahR $CUDA_CORE_CYTHON_TESTS_DIR

- name: Set up Python ${{ matrix.PY_VER }}

uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5.6.0

with:

python-version: ${{ matrix.PY_VER }}

env:

# we use self-hosted runners on which setup-python behaves weirdly...

AGENT_TOOLSDIRECTORY: "/opt/hostedtoolcache"

- name: Set up mini CTK

if: ${{ matrix.LOCAL_CTK == '1' }}

uses: ./.github/actions/fetch_ctk

continue-on-error: false

with:

host-platform: ${{ inputs.host-platform }}

cuda-version: ${{ matrix.CUDA_VER }}

- name: Set up latest cuda_sanitizer_api

if: ${{ env.SETUP_SANITIZER == '1' }}

uses: ./.github/actions/fetch_ctk

continue-on-error: false

with:

host-platform: ${{ inputs.host-platform }}

cuda-version: ${{ env.LATEST_CUDA_VERSION }}

cuda-components: "cuda_sanitizer_api"

- name: Set up compute-sanitizer

run: setup-sanitizer

- name: Run cuda.pathfinder tests with see_what_works

env:

CUDA_PATHFINDER_TEST_LOAD_NVIDIA_DYNAMIC_LIB_STRICTNESS: see_what_works

run: run-tests pathfinder

- name: Run cuda.bindings tests

if: ${{ env.SKIP_CUDA_BINDINGS_TEST == '0' }}

env:

CUDA_VER: ${{ matrix.CUDA_VER }}

LOCAL_CTK: ${{ matrix.LOCAL_CTK }}

run: run-tests bindings

- name: Run cuda.core tests

env:

CUDA_VER: ${{ matrix.CUDA_VER }}

LOCAL_CTK: ${{ matrix.LOCAL_CTK }}

run: run-tests core

- name: Ensure cuda-python installable

run: |

if [[ "${{ matrix.LOCAL_CTK }}" == 1 ]]; then

pip install cuda_python*.whl

else

pip install $(ls cuda_python*.whl)[all]

fi

- name: Install cuda.pathfinder nvidia_wheels_cu13

if: startsWith(matrix.CUDA_VER, '13.')

run: |

pushd cuda_pathfinder

pip install -v .[nvidia_wheels_cu13]

pip freeze

popd

- name: Run cuda.pathfinder tests with all_must_work

if: startsWith(matrix.CUDA_VER, '13.')

env:

CUDA_PATHFINDER_TEST_LOAD_NVIDIA_DYNAMIC_LIB_STRICTNESS: all_must_work

run: run-tests pathfinder