Skip to content

Commit bfd2482

Browse files
israbbaniisrabbani
authored
Merge branch 'master' into irabbani/cgroups-14
2 parents 60d77bb + 45ebb1a commit bfd2482

File tree

256 files changed

+10005
-7970
lines changed

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

256 files changed

+10005
-7970
lines changed

‎.buildkite/core.rayci.yml‎

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -2,6 +2,8 @@ group: core tests
22
depends_on:
33
- forge
44
- oss-ci-base_build
5+
- ray-core-build
6+
- ray-dashboard-build
57
steps:
68
# builds
79
- name: corebuild

‎.buildkite/data.rayci.yml‎

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -2,6 +2,8 @@ group: data tests
22
depends_on:
33
- forge
44
- oss-ci-base_ml
5+
- ray-core-build
6+
- ray-dashboard-build
57
steps:
68
# builds
79
- name: data9build

‎.buildkite/dependencies.rayci.yml‎

Lines changed: 9 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -38,3 +38,12 @@ steps:
3838
- bazel run //ci/raydepsets:raydepsets -- build ci/raydepsets/configs/rayimg.depsets.yaml --check
3939
job_env: manylinux
4040
depends_on: manylinux
41+
42+
- label: ":tapioca: build: raydepsets: compile multimodal inference release test dependencies"
43+
key: raydepsets_compile_multimodal_inference_release_test_dependencies
44+
tags: always
45+
instance_type: medium
46+
commands:
47+
- bazel run //ci/raydepsets:raydepsets -- build ci/raydepsets/configs/release_multimodal_inference_benchmarks_tests.depsets.yaml --check
48+
job_env: manylinux
49+
depends_on: manylinux

‎.buildkite/llm.rayci.yml‎

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -1,6 +1,8 @@
11
group: llm tests
22
depends_on:
33
- forge
4+
- ray-core-build
5+
- ray-dashboard-build
46
steps:
57
- name: llmbuild
68
wanda: ci/docker/llm.build.wanda.yaml

‎.buildkite/ml.rayci.yml‎

Lines changed: 30 additions & 13 deletions
Original file line numberDiff line numberDiff line change
@@ -1,4 +1,8 @@
11
group: ml tests
2+
depends_on:
3+
- forge
4+
- ray-core-build
5+
- ray-dashboard-build
26
steps:
37
# builds
48
- name: minbuild-ml
@@ -59,26 +63,39 @@ steps:
5963
tags: cibase
6064

6165
# tests
62-
- label: ":train: ml: train tests"
66+
- label: ":train: ml: train v1 tests"
6367
tags: train
6468
instance_type: large
6569
parallelism: 2
6670
commands:
6771
- bazel run //ci/ray_ci:test_in_docker -- //python/ray/train/... ml
6872
--workers "$${BUILDKITE_PARALLEL_JOB_COUNT}" --worker-id "$${BUILDKITE_PARALLEL_JOB}" --parallelism-per-worker 3
69-
--except-tags gpu_only,gpu,minimal,tune,doctest,needs_credentials,train_v2
73+
--except-tags gpu,minimal,tune,doctest,needs_credentials,train_v2,train_v2_gpu
7074
depends_on: [ "mlbuild", "forge" ]
7175

7276
- label: ":bullettrain_front: ml: train v2 tests"
7377
tags: train
7478
instance_type: large
79+
parallelism: 2
7580
commands:
7681
- bazel run //ci/ray_ci:test_in_docker -- //python/ray/train/... ml
77-
--parallelism-per-worker 3
82+
--workers "$${BUILDKITE_PARALLEL_JOB_COUNT}" --worker-id "$${BUILDKITE_PARALLEL_JOB}" --parallelism-per-worker 3
7883
--only-tags train_v2
79-
--except-tags gpu_only
84+
--except-tags needs_credentials
8085
depends_on: [ "mlbuild", "forge" ]
8186

87+
- label: ":bullettrain_front: ml: train v2 gpu tests"
88+
tags:
89+
- train
90+
- gpu
91+
instance_type: gpu-large
92+
commands:
93+
- bazel run //ci/ray_ci:test_in_docker -- //python/ray/train/... //doc/... ml
94+
--workers "$${BUILDKITE_PARALLEL_JOB_COUNT}" --worker-id "$${BUILDKITE_PARALLEL_JOB}" --parallelism-per-worker 2
95+
--build-name mlgpubuild
96+
--only-tags train_v2_gpu
97+
depends_on: [ "mlgpubuild", "forge" ]
98+
8299
- label: ":train: ml: {{matrix.python}} tests ({{matrix.worker_id}})"
83100
if: build.pull_request.labels includes "continuous-build" || pipeline.id == "0189e759-8c96-4302-b6b5-b4274406bf89" || pipeline.id == "018f4f1e-1b73-4906-9802-92422e3badaa"
84101
tags:
@@ -90,7 +107,7 @@ steps:
90107
- bazel run //ci/ray_ci:test_in_docker -- //python/ray/train/... //python/ray/tune/... //python/ray/air/... ml
91108
--workers 4 --worker-id {{matrix.worker_id}} --parallelism-per-worker 3
92109
--python-version {{matrix.python}}
93-
--except-tags gpu_only,gpu,minimal,doctest,needs_credentials,soft_imports,rllib
110+
--except-tags gpu,train_v2_gpu,minimal,doctest,needs_credentials,soft_imports,rllib
94111
depends_on:
95112
- mlbuild-multipy
96113
- forge
@@ -100,7 +117,7 @@ steps:
100117
python: ["3.12"]
101118
worker_id: ["0", "1", "2", "3"]
102119

103-
- label: ":train: ml: train gpu tests"
120+
- label: ":train: ml: train v1 gpu tests"
104121
tags:
105122
- train
106123
- gpu
@@ -110,7 +127,7 @@ steps:
110127
- bazel run //ci/ray_ci:test_in_docker -- //python/ray/train/... //python/ray/air/... //doc/... ml
111128
--workers "$${BUILDKITE_PARALLEL_JOB_COUNT}" --worker-id "$${BUILDKITE_PARALLEL_JOB}" --parallelism-per-worker 2
112129
--build-name mlgpubuild
113-
--only-tags gpu,gpu_only
130+
--only-tags gpu
114131
depends_on: [ "mlgpubuild", "forge" ]
115132

116133
- label: ":train: ml: train gpu {{matrix.python}} tests ({{matrix.worker_id}})"
@@ -124,7 +141,7 @@ steps:
124141
--workers 2 --worker-id {{matrix.worker_id}} --parallelism-per-worker 2
125142
--python-version {{matrix.python}}
126143
--build-name mlgpubuild-py{{matrix.python}}
127-
--only-tags gpu,gpu_only
144+
--only-tags gpu,train_v2_gpu
128145
--except-tags doctest
129146
depends_on: [ "mlgpubuild-multipy", "forge" ]
130147
matrix:
@@ -154,7 +171,7 @@ steps:
154171
commands:
155172
- bazel run //ci/ray_ci:test_in_docker -- //python/ray/tune/... ml
156173
--parallelism-per-worker 3
157-
--except-tags doctest,soft_imports,gpu_only,rllib
174+
--except-tags doctest,soft_imports,rllib
158175
depends_on: [ "mlbuild", "forge" ]
159176

160177
- label: ":train: ml: tune soft import tests"
@@ -186,7 +203,7 @@ steps:
186203
- bazel run //ci/ray_ci:test_in_docker -- //python/ray/train/... ml
187204
--parallelism-per-worker 3
188205
--only-tags tune
189-
--except-tags gpu_only,ray_air,gpu,doctest,needs_credentials
206+
--except-tags ray_air,gpu,doctest,needs_credentials
190207
depends_on: [ "mlbuild", "forge" ]
191208

192209
- label: ":train: ml: rllib+tune tests"
@@ -198,7 +215,7 @@ steps:
198215
- bazel run //ci/ray_ci:test_in_docker -- //python/ray/tune/... ml
199216
--parallelism-per-worker 3
200217
--only-tags rllib
201-
--except-tags gpu_only
218+
--except-tags gpu
202219
depends_on: [ "mlbuild", "forge" ]
203220

204221
- label: ":train: ml: release tests"
@@ -266,7 +283,7 @@ steps:
266283
commands:
267284
- bazel run //ci/ray_ci:test_in_docker -- //... ml --run-flaky-tests
268285
--parallelism-per-worker 2
269-
--except-tags gpu_only,gpu,needs_credentials
286+
--except-tags gpu,needs_credentials,train_v2_gpu
270287
depends_on: [ "mlbuild", "forge" ]
271288
soft_fail: true
272289

@@ -298,6 +315,6 @@ steps:
298315
- bazel run //ci/ray_ci:test_in_docker -- //... ml --run-flaky-tests
299316
--parallelism-per-worker 2
300317
--build-name mlgpubuild
301-
--only-tags gpu,gpu_only
318+
--only-tags gpu,train_v2_gpu
302319
depends_on: [ "mlgpubuild", "forge" ]
303320
soft_fail: true

‎.buildkite/others.rayci.yml‎

Lines changed: 4 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -18,7 +18,10 @@ steps:
1818
--only-tags doctest
1919
--except-tags gpu
2020
--parallelism-per-worker 3
21-
depends_on: doctestbuild
21+
depends_on:
22+
- doctestbuild
23+
- ray-core-build
24+
- ray-dashboard-build
2225

2326
# java
2427
- label: ":java: java tests"

‎.buildkite/release/build.rayci.yml‎

Lines changed: 3 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -73,6 +73,7 @@ steps:
7373
- label: ":tapioca: build: ray py{{matrix.python}}-{{matrix.platform}} image for release tests"
7474
key: anyscalebuild
7575
instance_type: release-medium
76+
mount_buildkite_agent: true
7677
tags:
7778
- oss
7879
commands:
@@ -100,6 +101,7 @@ steps:
100101
- label: ":tapioca: build: ray-llm py{{matrix}} image for release tests"
101102
key: anyscalellmbuild
102103
instance_type: release-medium
104+
mount_buildkite_agent: true
103105
tags:
104106
- oss
105107
commands:
@@ -115,6 +117,7 @@ steps:
115117
- label: ":tapioca: build: ray-ml py{{matrix}} image for release tests"
116118
key: anyscalemlbuild
117119
instance_type: release-medium
120+
mount_buildkite_agent: true
118121
tags:
119122
- oss
120123
commands:

‎.buildkite/rllib.rayci.yml‎

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -1,6 +1,8 @@
11
group: rllib tests
22
depends_on:
33
- forge
4+
- ray-core-build
5+
- ray-dashboard-build
46
steps:
57
# builds
68
- name: rllibbuild

‎.buildkite/serve.rayci.yml‎

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -2,6 +2,8 @@ group: serve tests
22
depends_on:
33
- forge
44
- oss-ci-base_build
5+
- ray-core-build
6+
- ray-dashboard-build
57
steps:
68
# builds
79
- name: servebuild

‎.github/CODEOWNERS‎

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -69,6 +69,8 @@
6969
# LLM
7070
/python/ray/llm/ @ray-project/ray-llm
7171
/python/ray/data/llm.py @ray-project/ray-llm
72+
/python/ray/dashboard/modules/metrics/dashboards/serve_llm_dashboard_panels.py @ray-project/ray-llm
73+
/python/ray/dashboard/modules/metrics/dashboards/serve_llm_grafana_dashboard_base.json @ray-project/ray-llm
7274

7375
# Ray Serve
7476
/python/ray/serve/ @ray-project/ray-serve

0 commit comments

Comments
 (0)