[CI] Run 4xB200 steps nightly only (#61541)

Signed-off-by: khluu <khluu000@gmail.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
Kevin H. Luu
2026-10-15 00:08:48 -07:00
committed by GitHub
co-authored by Claude Opus 5.5
parent 32feecd91f
commit 8f111b22ee
2 changed files with 5 additions and 0 deletions
@@ -4,6 +4,8 @@ depends_on:
steps:
- label: ":nvidia: (B200) Distributed MooncakeConnector PD accuracy"
key: distributed-mooncakeconnector-pd-accuracy-4-gpus
# Nightly only: 4-GPU B200 pods wait hours behind smaller jobs on per-PR runs.
optional: true
timeout_in_minutes: 10
working_dir: "/vllm-workspace/tests"
# Runs on b200-k8s because it is the only NVIDIA pool that can carry mooncake
@@ -22,6 +24,7 @@ steps:
mirror:
amd:
label: ":amd: (MI355) Distributed MooncakeConnector HIP PD accuracy"
optional: true
dind: false
device: mi355_4
num_devices: 4
+2
View File
@@ -161,6 +161,8 @@ steps:
- label: ":nvidia: (4xB200) Kimi K3 Prefix Cache"
key: kimi-k3-prefix-cache-4xb200
# Nightly only: 4-GPU B200 pods wait hours behind smaller jobs on per-PR runs.
optional: true
automatic_shard: true
timeout_in_minutes: 75
device: b200-k8s