anodyine/vllm-omni
1
0 Fork 0
Code Issues 4 Pull Requests 2 Actions Packages Projects Releases Wiki Activity

[CI] Migrate L4 jobs to l4-k8s and split by GPU count (#6890)

Browse Source 
Signed-off-by: wangyu <410167048@qq.com>
Co-authored-by: amy-why-3459 <wuhaiyan17@huawei.com>
This commit is contained in:
wangyuandamy-why-3459 authored and GitHub committed 2026-09-02 17:09:59 +08:00
1 parent 67ef0b64b9
commit b6e72f3879
7 files changed
+313 -63
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

.buildkite/cuda/test-nightly.yml
+28 -9
View File
@@ -13,7 +13,7 @@ steps:
steps:
- label: ":full_moon: Omni · Function Test with H100 · Single-GPU"
timeout_in_minutes: 90
timeout_in_minutes: 120
commands:
- pytest -sv tests/e2e --run-level "full_model" -m "full_model and H100 and omni and cards_1" --ignore=tests/e2e/accuracy --ignore=tests/e2e/online_serving/test_minicpmo_4_5_duplex_expansion.py
mirror_hardwares: h100_1
@@ -30,11 +30,11 @@ steps:
- pytest -s -v tests/e2e/online_serving/test_minicpmo_4_5_duplex_expansion.py -m "full_model and cuda and H100 and omni and cards_1" --run-level "full_model"
mirror_hardwares: h100_1
- label: ":full_moon: Omni · Doc Test with L4"
- label: ":full_moon: Omni · Doc Test with L4 · 4-GPU"
timeout_in_minutes: 90
commands:
- export VLLM_ALLOW_LONG_MAX_MODEL_LEN="1"
- pytest -s -v tests/examples/ -m "full_model and omni and L4" --run-level "full_model"
- pytest -s -v tests/examples/ -m "full_model and omni and L4 and cards_4" --run-level "full_model"
mirror_hardwares: l4_4
- label: ":full_moon: Omni · Doc Test with H100 · 2-GPU"
@@ -178,7 +178,7 @@ steps:
build.pull_request.labels includes "nightly-test"
steps:
- label: ":full_moon: Tiny Model Tests · Diffusion (Multi-GPU accelerations)"
- label: ":full_moon: Tiny Model Tests · Diffusion (Multi-GPU accelerations) · 2-GPU"
timeout_in_minutes: 30
# NOTE: Single-GPU (core_model) tiny model tests run on the ready label,
# so nightly only adds the multi-GPU parallelism configurations.
@@ -188,7 +188,14 @@ steps:
# for the CI, since these tests should pass irrespective of whether or not we use
# the full weights or not.
commands:
- timeout 25m pytest -sv tests/model_tests/diffusion -m 'full_model and cuda' --run-level "core_model"
- pytest -sv tests/model_tests/diffusion -m 'full_model and cuda and cards_2' --run-level "core_model"
mirror_hardwares: l4_2
- label: ":full_moon: Tiny Model Tests · Diffusion (Multi-GPU accelerations) · 4-GPU"
timeout_in_minutes: 30
# CFG+TP extra_test_groups request 2×2=4 devices (see get_required_device_count).
commands:
- pytest -sv tests/model_tests/diffusion -m 'full_model and cuda and cards_4' --run-level "core_model"
mirror_hardwares: l4_4
- group: ":card_index_dividers: Diffusion X2I(&A&T) Model Test"
@@ -220,10 +227,10 @@ steps:
--run-level "full_model"
mirror_hardwares: h100_2
- label: ":full_moon: Diffusion X2I(&A&T) · Function Test with L4 · Multi-GPU"
- label: ":full_moon: Diffusion X2I(&A&T) · Function Test with L4 · 4-GPU"
timeout_in_minutes: 120
commands:
- pytest -sv tests/e2e/ -k "not test_wan and not hunyuan" -m "full_model and diffusion and L4 and not cards_1" --run-level "full_model" --ignore=tests/e2e/accuracy
- pytest -sv tests/e2e/ -k "not test_wan and not hunyuan" -m "full_model and diffusion and L4 and cards_4" --run-level "full_model" --ignore=tests/e2e/accuracy
mirror_hardwares: l4_4
- label: ":full_moon: Diffusion X2I(&A&T) · Doc Test"
@@ -427,10 +434,22 @@ steps:
depends_on: upload-nightly-pipeline
if: build.env("NIGHTLY") == "1" || build.pull_request.labels includes "nightly-test"
steps:
- label: ":full_moon: Diffusion · Distributed Test with L4"
- label: ":full_moon: Diffusion · Distributed Test with L4 · 2-GPU"
timeout_in_minutes: 60
commands:
- pytest -sv tests/diffusion/distributed/ -m 'full_model and cuda and L4' --run-level "full_model"
- pytest -sv tests/diffusion/distributed/ -m 'full_model and cuda and L4 and cards_2' --run-level "full_model"
mirror_hardwares: l4_2
- label: ":full_moon: Diffusion · Distributed Test with L4 · 3-GPU"
timeout_in_minutes: 60
commands:
- pytest -sv tests/diffusion/distributed/ -m 'full_model and cuda and L4 and cards_3' --run-level "full_model"
mirror_hardwares: l4_3
- label: ":full_moon: Diffusion · Distributed Test with L4 · 4-GPU"
timeout_in_minutes: 60
commands:
- pytest -sv tests/diffusion/distributed/ -m 'full_model and cuda and L4 and cards_4' --run-level "full_model"
mirror_hardwares: l4_4
- label: ":full_moon: Diffusion · Distributed Test with H100 · 2-GPU"