Skip to content

chore: benchmark test run (draft) #1017

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
kahilam wants to merge 3 commits into
base: main
Choose a base branch
from
+26 −1
Draft

chore: benchmark test run (draft) #1017

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
350f0ce
chore: trigger benchmark test run
kahilam Apr 14, 2026
5884ebf
fix: default LLM_D_RELEASE to main for GA InferencePool API
kahilam Apr 15, 2026
609f932
fix: align EPP --pool-group with GA InferencePool API group
kahilam Apr 15, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion deploy/install.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -47,7 +47,7 @@ CONTROLLER_INSTANCE=${CONTROLLER_INSTANCE:-""}
# llm-d Configuration
LLM_D_OWNER=${LLM_D_OWNER:-"llm-d"}
LLM_D_PROJECT=${LLM_D_PROJECT:-"llm-d"}
LLM_D_RELEASE=${LLM_D_RELEASE:-"v0.3.0"}
LLM_D_RELEASE=${LLM_D_RELEASE:-"main"}
LLM_D_MODELSERVICE_NAME=${LLM_D_MODELSERVICE_NAME:-"ms-$WELL_LIT_PATH_NAME-llm-d-modelservice"}
LLM_D_EPP_NAME=${LLM_D_EPP_NAME:-"gaie-$WELL_LIT_PATH_NAME-epp"}
CLIENT_PREREQ_DIR=${CLIENT_PREREQ_DIR:-"$WVA_PROJECT/$LLM_D_PROJECT/guides/prereq/client-setup"}
Expand Down
25 changes: 25 additions & 0 deletions deploy/lib/infra_llmd.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -310,6 +310,31 @@ deploy_llm_d_infrastructure() {
log_info "Skipping image patch: llm-d-inference-scheduler already using $LLM_D_INFERENCE_SCHEDULER_IMG"
fi

# Align EPP --pool-group with the GA InferencePool API group.
# The inferencepool Helm chart v1.4.0 creates InferencePool in
# inference.networking.k8s.io/v1, but the llm-d-inference-scheduler
# image defaults --pool-group to inference.networking.x-k8s.io.
local TARGET_POOL_GROUP="inference.networking.k8s.io"
if kubectl get deployment "$LLM_D_EPP_NAME" -n "$LLMD_NS" -o json \
| jq -e --arg group "$TARGET_POOL_GROUP" \
'.spec.template.spec.containers[0].args | any(. == $group)' &>/dev/null; then
log_info "EPP --pool-group already set to $TARGET_POOL_GROUP"
else
log_info "Patching EPP --pool-group to $TARGET_POOL_GROUP (GA InferencePool API)"
local NEW_ARGS
NEW_ARGS=$(kubectl get deployment "$LLM_D_EPP_NAME" -n "$LLMD_NS" -o json \
| jq -c --arg group "$TARGET_POOL_GROUP" '
.spec.template.spec.containers[0].args as $a |
[range(0; $a | length) | . as $i | $a[$i] |
select(. != "--pool-group") |
select($i == 0 or $a[$i - 1] != "--pool-group") |
select(startswith("--pool-group=") | not)
] + ["--pool-group", $group]')
kubectl patch deployment "$LLM_D_EPP_NAME" -n "$LLMD_NS" --type='json' \
-p="[{\"op\": \"replace\", \"path\": \"/spec/template/spec/containers/0/args\", \"value\": $NEW_ARGS}]"
log_success "EPP --pool-group patched to $TARGET_POOL_GROUP"
fi

# Enable flowControl feature gate in the EPP ConfigMap
if kubectl get configmap "$LLM_D_EPP_NAME" -n "$LLMD_NS" &> /dev/null; then
# Check if flowControl is already enabled
Expand Down
Loading