Skip to content
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

fix hardcoded request type #670

Merged
merged 1 commit into from
May 16, 2024
Merged

fix hardcoded request type #670

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
5 changes: 5 additions & 0 deletions benchmarks/benchmark/tools/locust-load-inference/locust-docker/locust-tasks/run.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,6 +14,8 @@
# See the License for the specific language governing permissions and
# limitations under the License.

echo "starting locust for $LOCUST_MODE"

LOCUST="/usr/local/bin/locust"
LOCUST_OPTS="-f /locust-tasks/tasks.py "
LOCUST_MODE=${LOCUST_MODE:-standalone}
Expand All @@ -35,7 +37,10 @@ if [[ "$LOCUST_MODE" = "master" ]]; then
LOCUST_OPTS="$LOCUST_OPTS --stop-timeout $STOP_TIMEOUT"
fi
elif [[ "$LOCUST_MODE" = "worker" ]]; then

echo "login to huggingface"
huggingface-cli login --token $HUGGINGFACE_TOKEN
annapendleton marked this conversation as resolved.
Show resolved Hide resolved

FILTER_PROMPTS="python /locust-tasks/load_data.py"
FILTER_PROMPTS_OPTS="--gcs_path=$GCS_PATH --tokenizer=$TOKENIZER --max_prompt_len=$MAX_PROMPT_LEN --max_num_prompts=$MAX_NUM_PROMPTS"
echo "$FILTER_PROMPTS $FILTER_PROMPTS_OPTS"
Expand Down
1 change: 1 addition & 0 deletions benchmarks/benchmark/tools/locust-load-inference/main.tf
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -48,6 +48,7 @@ locals {
use_beam_search = var.use_beam_search
hugging_face_token_secret_list = local.hugging_face_token_secret == null ? [] : [local.hugging_face_token_secret]
stop_timeout = var.stop_timeout
request_type = var.request_type
})) : data]
])
}
Expand Down
2 changes: 1 addition & 1 deletion ...enchmark/tools/locust-load-inference/manifest-templates/locust-master-controller.yaml.tpl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,7 +30,7 @@ spec:
- name: STOP_TIMEOUT
value: ${stop_timeout}
- name: REQUEST_TYPE
value: grpc
value: ${request_type}
ports:
- name: loc-master-web
containerPort: 8089
Expand Down
2 changes: 1 addition & 1 deletion ...enchmark/tools/locust-load-inference/manifest-templates/locust-worker-controller.yaml.tpl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,7 +24,7 @@ spec:
- name: LOCUST_MODE
value: worker
- name: REQUEST_TYPE
value: grpc
value: ${request_type}
- name: LOCUST_MASTER
value: locust-master
- name: TARGET_HOST
Expand Down
2 changes: 1 addition & 1 deletion benchmarks/benchmark/tools/locust-load-inference/sample-terraform.tfvars
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,7 +9,7 @@ ksa = "benchmark-ksa"

# Locust service configuration
artifact_registry = "us-central1-docker.pkg.dev/$PROJECT_ID/ai-benchmark"
inference_server_service = "tgi" # inference server service name
inference_server_service = "http://tgi" # inference server service name
annapendleton marked this conversation as resolved.
Show resolved Hide resolved
annapendleton marked this conversation as resolved.
Show resolved Hide resolved
locust_runner_kubernetes_service_account = "sample-runner-ksa"
output_bucket = "benchmark-output"
gcs_path = "gs://${PROJECT_ID}-ai-gke-benchmark-fuse/ShareGPT_V3_unfiltered_cleaned_split_filtered_prompts.txt"
Expand Down