forked from pytorch/pytorch
-
Notifications
You must be signed in to change notification settings - Fork 0
352 lines (326 loc) · 18 KB
/
periodic.yml
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
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
name: periodic
on:
schedule:
# We have several schedules so jobs can check github.event.schedule to activate only for a fraction of the runs.
# Also run less frequently on weekends.
- cron: 45 0,8,16 * * 1-5
- cron: 45 4 * * 0,6
- cron: 45 4,12,20 * * 1-5
- cron: 45 12 * * 0,6
- cron: 29 8 * * * # about 1:29am PDT, for mem leak check and rerun disabled tests
push:
tags:
- ciflow/periodic/*
branches:
- release/*
workflow_dispatch:
concurrency:
group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref_name }}-${{ github.ref_type == 'branch' && github.sha }}-${{ github.event_name == 'workflow_dispatch' }}-${{ github.event_name == 'schedule' }}-${{ github.event.schedule }}
cancel-in-progress: true
permissions: read-all
jobs:
llm-td:
if: github.repository_owner == 'pytorch'
name: before-test
uses: ./.github/workflows/llm_td_retrieval.yml
permissions:
id-token: write
contents: read
target-determination:
name: before-test
uses: ./.github/workflows/target_determination.yml
needs: llm-td
permissions:
id-token: write
contents: read
get-label-type:
name: get-label-type
uses: pytorch/pytorch/.github/workflows/_runner-determinator.yml@main
if: (github.event_name != 'schedule' || github.repository == 'pytorch/pytorch') && github.repository_owner == 'pytorch'
with:
triggering_actor: ${{ github.triggering_actor }}
issue_owner: ${{ github.event.pull_request.user.login || github.event.issue.user.login }}
curr_branch: ${{ github.head_ref || github.ref_name }}
curr_ref_type: ${{ github.ref_type }}
linux-focal-cuda12_1-py3_10-gcc9-build:
name: linux-focal-cuda12.1-py3.10-gcc9
uses: ./.github/workflows/_linux-build.yml
needs: get-label-type
with:
runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
build-environment: linux-focal-cuda12.1-py3.10-gcc9
docker-image-name: pytorch-linux-focal-cuda12.1-cudnn9-py3-gcc9
test-matrix: |
{ include: [
{ config: "nogpu_AVX512", shard: 1, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.4xlarge" },
{ config: "nogpu_AVX512", shard: 2, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.4xlarge" },
{ config: "nogpu_NO_AVX2", shard: 1, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.4xlarge" },
{ config: "nogpu_NO_AVX2", shard: 2, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.4xlarge" },
{ config: "jit_legacy", shard: 1, num_shards: 1, runner: "${{ needs.get-label-type.outputs.label-type }}linux.4xlarge.nvidia.gpu" },
]}
secrets: inherit
linux-focal-cuda12_1-py3_10-gcc9-test:
name: linux-focal-cuda12.1-py3.10-gcc9
uses: ./.github/workflows/_linux-test.yml
needs:
- linux-focal-cuda12_1-py3_10-gcc9-build
- target-determination
with:
build-environment: linux-focal-cuda12.1-py3.10-gcc9
docker-image: ${{ needs.linux-focal-cuda12_1-py3_10-gcc9-build.outputs.docker-image }}
test-matrix: ${{ needs.linux-focal-cuda12_1-py3_10-gcc9-build.outputs.test-matrix }}
secrets: inherit
linux-focal-cuda12_4-py3_10-gcc9-build:
name: linux-focal-cuda12.4-py3.10-gcc9
uses: ./.github/workflows/_linux-build.yml
needs: get-label-type
with:
runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
build-environment: linux-focal-cuda12.4-py3.10-gcc9
docker-image-name: pytorch-linux-focal-cuda12.4-cudnn9-py3-gcc9
test-matrix: |
{ include: [
{ config: "default", shard: 1, num_shards: 5, runner: "${{ needs.get-label-type.outputs.label-type }}linux.4xlarge.nvidia.gpu" },
{ config: "default", shard: 2, num_shards: 5, runner: "${{ needs.get-label-type.outputs.label-type }}linux.4xlarge.nvidia.gpu" },
{ config: "default", shard: 3, num_shards: 5, runner: "${{ needs.get-label-type.outputs.label-type }}linux.4xlarge.nvidia.gpu" },
{ config: "default", shard: 4, num_shards: 5, runner: "${{ needs.get-label-type.outputs.label-type }}linux.4xlarge.nvidia.gpu" },
{ config: "default", shard: 5, num_shards: 5, runner: "${{ needs.get-label-type.outputs.label-type }}linux.4xlarge.nvidia.gpu" },
{ config: "nogpu_AVX512", shard: 1, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.4xlarge" },
{ config: "nogpu_AVX512", shard: 2, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.4xlarge" },
{ config: "nogpu_NO_AVX2", shard: 1, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.4xlarge" },
{ config: "nogpu_NO_AVX2", shard: 2, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.4xlarge" },
{ config: "jit_legacy", shard: 1, num_shards: 1, runner: "${{ needs.get-label-type.outputs.label-type }}linux.4xlarge.nvidia.gpu" },
]}
secrets: inherit
linux-focal-cuda12_4-py3_10-gcc9-test:
name: linux-focal-cuda12.4-py3.10-gcc9
uses: ./.github/workflows/_linux-test.yml
needs:
- linux-focal-cuda12_4-py3_10-gcc9-build
- target-determination
with:
timeout-minutes: 360
build-environment: linux-focal-cuda12.4-py3.10-gcc9
docker-image: ${{ needs.linux-focal-cuda12_4-py3_10-gcc9-build.outputs.docker-image }}
test-matrix: ${{ needs.linux-focal-cuda12_4-py3_10-gcc9-build.outputs.test-matrix }}
secrets: inherit
linux-focal-cuda11_8-py3_9-gcc9-build:
name: linux-focal-cuda11.8-py3.9-gcc9
uses: ./.github/workflows/_linux-build.yml
needs: get-label-type
with:
runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
build-environment: linux-focal-cuda11.8-py3.9-gcc9
docker-image-name: pytorch-linux-focal-cuda11.8-cudnn9-py3-gcc9
cuda-arch-list: 8.6
test-matrix: |
{ include: [
{ config: "multigpu", shard: 1, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g5.12xlarge.nvidia.gpu", owners: ["oncall:distributed"] },
{ config: "multigpu", shard: 2, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g5.12xlarge.nvidia.gpu", owners: ["oncall:distributed"] },
]}
build-with-debug: false
secrets: inherit
linux-focal-cuda11_8-py3_9-gcc9-test:
name: linux-focal-cuda11.8-py3.9-gcc9
uses: ./.github/workflows/_linux-test.yml
needs: linux-focal-cuda11_8-py3_9-gcc9-build
with:
build-environment: linux-focal-cuda11.8-py3.9-gcc9
docker-image: ${{ needs.linux-focal-cuda11_8-py3_9-gcc9-build.outputs.docker-image }}
test-matrix: ${{ needs.linux-focal-cuda11_8-py3_9-gcc9-build.outputs.test-matrix }}
secrets: inherit
linux-focal-cuda11_8-py3_10-gcc9-debug-build:
name: linux-focal-cuda11.8-py3.10-gcc9-debug
uses: ./.github/workflows/_linux-build.yml
needs: get-label-type
with:
runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
build-environment: linux-focal-cuda11.8-py3.10-gcc9-debug
docker-image-name: pytorch-linux-focal-cuda11.8-cudnn9-py3-gcc9
build-with-debug: true
test-matrix: |
{ include: [
{ config: "default", shard: 1, num_shards: 7, runner: "${{ needs.get-label-type.outputs.label-type }}linux.4xlarge.nvidia.gpu", owners: ["oncall:debug-build"] },
{ config: "default", shard: 2, num_shards: 7, runner: "${{ needs.get-label-type.outputs.label-type }}linux.4xlarge.nvidia.gpu", owners: ["oncall:debug-build"] },
{ config: "default", shard: 3, num_shards: 7, runner: "${{ needs.get-label-type.outputs.label-type }}linux.4xlarge.nvidia.gpu", owners: ["oncall:debug-build"] },
{ config: "default", shard: 4, num_shards: 7, runner: "${{ needs.get-label-type.outputs.label-type }}linux.4xlarge.nvidia.gpu", owners: ["oncall:debug-build"] },
{ config: "default", shard: 5, num_shards: 7, runner: "${{ needs.get-label-type.outputs.label-type }}linux.4xlarge.nvidia.gpu", owners: ["oncall:debug-build"] },
{ config: "default", shard: 6, num_shards: 7, runner: "${{ needs.get-label-type.outputs.label-type }}linux.4xlarge.nvidia.gpu", owners: ["oncall:debug-build"] },
{ config: "default", shard: 7, num_shards: 7, runner: "${{ needs.get-label-type.outputs.label-type }}linux.4xlarge.nvidia.gpu", owners: ["oncall:debug-build"] },
]}
secrets: inherit
linux-focal-cuda11_8-py3_10-gcc9-debug-test:
name: linux-focal-cuda11.8-py3.10-gcc9-debug
uses: ./.github/workflows/_linux-test.yml
needs:
- linux-focal-cuda11_8-py3_10-gcc9-debug-build
- target-determination
with:
build-environment: linux-focal-cuda11.8-py3.10-gcc9-debug
docker-image: ${{ needs.linux-focal-cuda11_8-py3_10-gcc9-debug-build.outputs.docker-image }}
test-matrix: ${{ needs.linux-focal-cuda11_8-py3_10-gcc9-debug-build.outputs.test-matrix }}
secrets: inherit
linux-focal-rocm6_2-py3_10-build:
name: linux-focal-rocm6.2-py3.10
uses: ./.github/workflows/_linux-build.yml
needs: get-label-type
with:
runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
build-environment: linux-focal-rocm6.2-py3.10
docker-image-name: pytorch-linux-focal-rocm-n-py3
test-matrix: |
{ include: [
{ config: "distributed", shard: 1, num_shards: 3, runner: "linux.rocm.gpu.4", owners: ["module:rocm", "oncall:distributed"] },
{ config: "distributed", shard: 2, num_shards: 3, runner: "linux.rocm.gpu.4", owners: ["module:rocm", "oncall:distributed"] },
{ config: "distributed", shard: 3, num_shards: 3, runner: "linux.rocm.gpu.4", owners: ["module:rocm", "oncall:distributed"] },
]}
secrets: inherit
linux-focal-rocm6_2-py3_10-test:
permissions:
id-token: write
contents: read
name: linux-focal-rocm6.2-py3.10
uses: ./.github/workflows/_rocm-test.yml
needs:
- linux-focal-rocm6_2-py3_10-build
- target-determination
with:
build-environment: linux-focal-rocm6.2-py3.10
docker-image: ${{ needs.linux-focal-rocm6_2-py3_10-build.outputs.docker-image }}
test-matrix: ${{ needs.linux-focal-rocm6_2-py3_10-build.outputs.test-matrix }}
secrets: inherit
linux-focal-cuda12_1-py3_10-gcc9-experimental-split-build:
name: linux-focal-cuda12.1-py3.10-gcc9-experimental-split-build
uses: ./.github/workflows/_linux-build.yml
needs: get-label-type
if: false # See https://github.com/pytorch/pytorch/issues/138750
with:
runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
use_split_build: true
build-environment: linux-focal-cuda12.1-py3.10-gcc9
docker-image-name: pytorch-linux-focal-cuda12.1-cudnn9-py3-gcc9
test-matrix: |
{ include: [
{ config: "nogpu_AVX512", shard: 1, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.4xlarge" },
{ config: "nogpu_AVX512", shard: 2, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.4xlarge" },
{ config: "nogpu_NO_AVX2", shard: 1, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.4xlarge" },
{ config: "nogpu_NO_AVX2", shard: 2, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.4xlarge" },
{ config: "jit_legacy", shard: 1, num_shards: 1, runner: "${{ needs.get-label-type.outputs.label-type }}linux.4xlarge.nvidia.gpu" },
]}
secrets: inherit
linux-focal-cuda12_1-py3_10-gcc9-experimental-split-build-test:
name: linux-focal-cuda12.1-py3.10-gcc9-experimental-split-build
uses: ./.github/workflows/_linux-test.yml
needs:
- linux-focal-cuda12_1-py3_10-gcc9-experimental-split-build
- target-determination
with:
build-environment: linux-focal-cuda12.1-py3.10-gcc9-experimental-split-build
docker-image: ${{ needs.linux-focal-cuda12_1-py3_10-gcc9-experimental-split-build.outputs.docker-image }}
test-matrix: ${{ needs.linux-focal-cuda12_1-py3_10-gcc9-experimental-split-build.outputs.test-matrix }}
secrets: inherit
linux-focal-cuda11_8-py3_9-gcc9-experimental-split-build:
name: linux-focal-cuda11.8-py3.9-gcc9-experimental-split-build
uses: ./.github/workflows/_linux-build.yml
needs: get-label-type
if: false # See https://github.com/pytorch/pytorch/issues/138750
with:
runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
use_split_build: true
build-environment: linux-focal-cuda11.8-py3.9-gcc9
docker-image-name: pytorch-linux-focal-cuda11.8-cudnn9-py3-gcc9
cuda-arch-list: 8.6
test-matrix: |
{ include: [
{ config: "multigpu", shard: 1, num_shards: 1, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g5.12xlarge.nvidia.gpu", owners: ["oncall:distributed"] },
]}
build-with-debug: false
secrets: inherit
linux-focal-cuda11_8-py3_9-gcc9-experimental-split-build-test:
name: linux-focal-cuda11.8-py3.9-gcc9-experimental-split-build-test
uses: ./.github/workflows/_linux-test.yml
needs:
- linux-focal-cuda11_8-py3_9-gcc9-experimental-split-build
- target-determination
with:
build-environment: linux-focal-cuda11.8-py3.9-gcc9-experimental-split-build
docker-image: ${{ needs.linux-focal-cuda11_8-py3_9-gcc9-experimental-split-build.outputs.docker-image }}
test-matrix: ${{ needs.linux-focal-cuda11_8-py3_9-gcc9-experimental-split-build.outputs.test-matrix }}
secrets: inherit
linux-focal-cuda11_8-py3_10-gcc9-experimental-split-build:
name: linux-focal-cuda11.8-py3.10-gcc9-experimental-split-build
uses: ./.github/workflows/_linux-build.yml
needs: get-label-type
if: false # See https://github.com/pytorch/pytorch/issues/138750
with:
runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
use_split_build: true
build-environment: linux-focal-cuda11.8-py3.10-gcc9
docker-image-name: pytorch-linux-focal-cuda11.8-cudnn9-py3-gcc9
cuda-arch-list: '7.5'
test-matrix: |
{ include: [
{ config: "distributed", shard: 1, num_shards: 3, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g4dn.12xlarge.nvidia.gpu", owners: ["oncall:distributed"] },
{ config: "distributed", shard: 2, num_shards: 3, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g4dn.12xlarge.nvidia.gpu", owners: ["oncall:distributed"] },
{ config: "distributed", shard: 3, num_shards: 3, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g4dn.12xlarge.nvidia.gpu", owners: ["oncall:distributed"] },
]}
secrets: inherit
linux-focal-cuda11_8-py3_10-gcc9-experimental-split-build-test:
name: linux-focal-cuda11.8-py3.10-gcc9-experimental-split-build-test
uses: ./.github/workflows/_linux-test.yml
needs:
- linux-focal-cuda11_8-py3_10-gcc9-experimental-split-build
- target-determination
with:
timeout-minutes: 360
build-environment: linux-focal-cuda11.8-py3.10-gcc9-experimental-split-build
docker-image: ${{ needs.linux-focal-cuda11_8-py3_10-gcc9-experimental-split-build.outputs.docker-image }}
test-matrix: ${{ needs.linux-focal-cuda11_8-py3_10-gcc9-experimental-split-build.outputs.test-matrix }}
secrets: inherit
linux-focal-cuda12_1-py3-gcc9-slow-gradcheck-build:
name: linux-focal-cuda12.1-py3-gcc9-slow-gradcheck
uses: ./.github/workflows/_linux-build.yml
needs: get-label-type
with:
runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
build-environment: linux-focal-cuda12.1-py3-gcc9-slow-gradcheck
docker-image-name: pytorch-linux-focal-cuda12.1-cudnn9-py3-gcc9
cuda-arch-list: 8.6
test-matrix: |
{ include: [
{ config: "default", shard: 1, num_shards: 8, runner: "linux.g5.4xlarge.nvidia.gpu", owners: ["module:slowgradcheck"] },
{ config: "default", shard: 2, num_shards: 8, runner: "linux.g5.4xlarge.nvidia.gpu", owners: ["module:slowgradcheck"] },
{ config: "default", shard: 3, num_shards: 8, runner: "linux.g5.4xlarge.nvidia.gpu", owners: ["module:slowgradcheck"] },
{ config: "default", shard: 4, num_shards: 8, runner: "linux.g5.4xlarge.nvidia.gpu", owners: ["module:slowgradcheck"] },
{ config: "default", shard: 5, num_shards: 8, runner: "linux.g5.4xlarge.nvidia.gpu", owners: ["module:slowgradcheck"] },
{ config: "default", shard: 6, num_shards: 8, runner: "linux.g5.4xlarge.nvidia.gpu", owners: ["module:slowgradcheck"] },
{ config: "default", shard: 7, num_shards: 8, runner: "linux.g5.4xlarge.nvidia.gpu", owners: ["module:slowgradcheck"] },
{ config: "default", shard: 8, num_shards: 8, runner: "linux.g5.4xlarge.nvidia.gpu", owners: ["module:slowgradcheck"] },
]}
secrets: inherit
linux-focal-cuda12_1-py3-gcc9-slow-gradcheck-test:
name: linux-focal-cuda12.1-py3-gcc9-slow-gradcheck
uses: ./.github/workflows/_linux-test.yml
needs:
- linux-focal-cuda12_1-py3-gcc9-slow-gradcheck-build
- target-determination
with:
build-environment: linux-focal-cuda12.1-py3-gcc9-slow-gradcheck
docker-image: ${{ needs.linux-focal-cuda12_1-py3-gcc9-slow-gradcheck-build.outputs.docker-image }}
test-matrix: ${{ needs.linux-focal-cuda12_1-py3-gcc9-slow-gradcheck-build.outputs.test-matrix }}
timeout-minutes: 300
secrets: inherit
linux-focal-cuda12_4-py3_10-gcc9-bazel-test:
name: linux-focal-cuda12.4-py3.10-gcc9-bazel-test
uses: ./.github/workflows/_bazel-build-test.yml
needs: get-label-type
with:
runner: "${{ needs.get-label-type.outputs.label-type }}linux.large"
build-environment: linux-focal-cuda12.4-py3.10-gcc9-bazel-test
docker-image-name: pytorch-linux-focal-cuda12.4-cudnn9-py3-gcc9
cuda-version: "12.4"
test-matrix: |
{ include: [
{ config: "default", shard: 1, num_shards: 1, runner: "${{ needs.get-label-type.outputs.label-type }}linux.4xlarge.nvidia.gpu" },
]}
secrets: inherit