Skip to content

Commit d5fb3a3

Browse files
Partial enablement of CICD for GKE (llm-d#934)
Signed-off-by: maugustosilva <maugusto.silva@gmail.com>
1 parent 5322c74 commit d5fb3a3

2 files changed

Lines changed: 2 additions & 2 deletions

File tree

.github/workflows/nightly-e2e-inference-scheduling-gke.yaml

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -33,7 +33,7 @@ jobs:
3333
gke_cluster_zone: us-east5
3434
required_gpus: 2
3535
recommended_gpus: 4
36-
accelerator_type: L4
36+
accelerator_type: H100
3737
pod_wait_timeout: '30m'
3838
pod_readiness_delay: 180
3939
httproute_file: httproute.gke.yaml

.github/workflows/nightly-e2e-pd-disaggregation-gke.yaml

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -34,7 +34,7 @@ jobs:
3434
gke_cluster_zone: us-east5
3535
required_gpus: 2
3636
recommended_gpus: 4
37-
accelerator_type: L4
37+
accelerator_type: H100
3838
pod_wait_timeout: '30m'
3939
pod_readiness_delay: 180
4040
httproute_file: httproute.gke.yaml

0 commit comments

Comments
 (0)