Sync value files from GenAIInfra (#1428)

All gaudi values updated with extra flags.
Added helm support for 2 new examples Text2Image and SearchQnA. Minor fix for llm-uservice.

Signed-off-by: Dolpher Du <dolpher.du@intel.com>

CodeTrans/kubernetes/helm/gaudi-values.yaml

@@ -5,13 +5,18 @@ tgi:
   accelDevice: "gaudi"
   image:
     repository: ghcr.io/huggingface/tgi-gaudi
-    tag: "2.0.6"
+    tag: "2.3.1"
   resources:
     limits:
       habana.ai/gaudi: 1
   MAX_INPUT_LENGTH: "1024"
   MAX_TOTAL_TOKENS: "2048"
   CUDA_GRAPHS: ""
+  OMPI_MCA_btl_vader_single_copy_mechanism: "none"
+  ENABLE_HPU_GRAPH: "true"
+  LIMIT_HPU_GRAPH: "true"
+  USE_FLASH_ATTENTION: "true"
+  FLASH_ATTENTION_RECOMPUTE: "true"
   livenessProbe:
     initialDelaySeconds: 5
     periodSeconds: 5

CodeTrans/tests/test_manifest_on_gaudi.sh

@@ -1,86 +0,0 @@
-#!/bin/bash
-# Copyright (C) 2024 Intel Corporation
-# SPDX-License-Identifier: Apache-2.0
-
-set -xe
-USER_ID=$(whoami)
-LOG_PATH=/home/$(whoami)/logs
-MOUNT_DIR=/home/$USER_ID/.cache/huggingface/hub
-IMAGE_REPO=${IMAGE_REPO:-opea}
-IMAGE_TAG=${IMAGE_TAG:-latest}
-
-function init_codetrans() {
-    # executed under path manifest/codetrans/xeon
-    # replace the mount dir "path: /mnt/model" with "path: $CHART_MOUNT"
-    find . -name '*.yaml' -type f -exec sed -i "s#path: /mnt/opea-models#path: $MOUNT_DIR#g" {} \;
-    # replace microservice image tag
-    find . -name '*.yaml' -type f -exec sed -i "s#image: \"opea/\(.*\):latest#image: \"opea/\1:${IMAGE_TAG}#g" {} \;
-    # replace the repository "image: opea/*" with "image: $IMAGE_REPO/"
-    find . -name '*.yaml' -type f -exec sed -i "s#image: \"opea/*#image: \"${IMAGE_REPO}/#g" {} \;
-    # set huggingface token
-    find . -name '*.yaml' -type f -exec sed -i "s#insert-your-huggingface-token-here#$(cat /home/$USER_ID/.cache/huggingface/token)#g" {} \;
-}
-
-function install_codetrans {
-    echo "namespace is $NAMESPACE"
-    kubectl apply -f codetrans.yaml -n $NAMESPACE
-}
-
-function validate_codetrans() {
-    ip_address=$(kubectl get svc $SERVICE_NAME -n $NAMESPACE -o jsonpath='{.spec.clusterIP}')
-    port=$(kubectl get svc $SERVICE_NAME -n $NAMESPACE -o jsonpath='{.spec.ports[0].port}')
-    echo "try to curl http://${ip_address}:${port}/v1/codetrans..."
-
-    # generate a random logfile name to avoid conflict among multiple runners
-    LOGFILE=$LOG_PATH/curlmega_$NAMESPACE.log
-    # Curl the Mega Service
-    curl http://${ip_address}:${port}/v1/codetrans \
-    -H 'Content-Type: application/json' \
-    -d '{"language_from": "Golang","language_to": "Python","source_code": "package main\n\nimport \"fmt\"\nfunc main() {\n    fmt.Println(\"Hello, World!\");\n}"}' > $LOGFILE
-    exit_code=$?
-    if [ $exit_code -ne 0 ]; then
-        echo "Megaservice codetrans failed, please check the logs in $LOGFILE!"
-        exit 1
-    fi
-
-    echo "Checking response results, make sure the output is reasonable. "
-    local status=false
-    if [[ -f $LOGFILE ]] && \
-    [[ $(grep -c "print" $LOGFILE) != 0 ]]; then
-        status=true
-    fi
-
-    if [ $status == false ]; then
-        echo "Response check failed, please check the logs in artifacts!"
-        exit 1
-    else
-        echo "Response check succeed!"
-    fi
-}
-
-if [ $# -eq 0 ]; then
-    echo "Usage: $0 <function_name>"
-    exit 1
-fi
-
-case "$1" in
-    init_CodeTrans)
-        pushd CodeTrans/kubernetes/intel/hpu/gaudi/manifest
-        init_codetrans
-        popd
-        ;;
-    install_CodeTrans)
-        pushd CodeTrans/kubernetes/intel/hpu/gaudi/manifest
-        NAMESPACE=$2
-        install_codetrans
-        popd
-        ;;
-    validate_CodeTrans)
-        NAMESPACE=$2
-        SERVICE_NAME=codetrans
-        validate_codetrans
-        ;;
-    *)
-        echo "Unknown function: $1"
-        ;;
-esac

CodeTrans/tests/test_manifest_on_xeon.sh

@@ -1,86 +0,0 @@
-#!/bin/bash
-# Copyright (C) 2024 Intel Corporation
-# SPDX-License-Identifier: Apache-2.0
-
-set -xe
-USER_ID=$(whoami)
-LOG_PATH=/home/$(whoami)/logs
-MOUNT_DIR=/home/$USER_ID/.cache/huggingface/hub
-IMAGE_REPO=${IMAGE_REPO:-opea}
-IMAGE_TAG=${IMAGE_TAG:-latest}
-
-function init_codetrans() {
-    # executed under path manifest/codetrans/xeon
-    # replace the mount dir "path: /mnt/model" with "path: $CHART_MOUNT"
-    find . -name '*.yaml' -type f -exec sed -i "s#path: /mnt/opea-models#path: $MOUNT_DIR#g" {} \;
-    # replace microservice image tag
-    find . -name '*.yaml' -type f -exec sed -i "s#image: \"opea/\(.*\):latest#image: \"opea/\1:${IMAGE_TAG}#g" {} \;
-    # replace the repository "image: opea/*" with "image: $IMAGE_REPO/"
-    find . -name '*.yaml' -type f -exec sed -i "s#image: \"opea/*#image: \"${IMAGE_REPO}/#g" {} \;
-    # set huggingface token
-    find . -name '*.yaml' -type f -exec sed -i "s#insert-your-huggingface-token-here#$(cat /home/$USER_ID/.cache/huggingface/token)#g" {} \;
-}
-
-function install_codetrans {
-    echo "namespace is $NAMESPACE"
-    kubectl apply -f codetrans.yaml -n $NAMESPACE
-}
-
-function validate_codetrans() {
-    ip_address=$(kubectl get svc $SERVICE_NAME -n $NAMESPACE -o jsonpath='{.spec.clusterIP}')
-    port=$(kubectl get svc $SERVICE_NAME -n $NAMESPACE -o jsonpath='{.spec.ports[0].port}')
-    echo "try to curl http://${ip_address}:${port}/v1/codetrans..."
-
-    # generate a random logfile name to avoid conflict among multiple runners
-    LOGFILE=$LOG_PATH/curlmega_$NAMESPACE.log
-    # Curl the Mega Service
-    curl http://${ip_address}:${port}/v1/codetrans \
-    -H 'Content-Type: application/json' \
-    -d '{"language_from": "Golang","language_to": "Python","source_code": "package main\n\nimport \"fmt\"\nfunc main() {\n    fmt.Println(\"Hello, World!\");\n}"}' > $LOGFILE
-    exit_code=$?
-    if [ $exit_code -ne 0 ]; then
-        echo "Megaservice codetrans failed, please check the logs in $LOGFILE!"
-        exit 1
-    fi
-
-    echo "Checking response results, make sure the output is reasonable. "
-    local status=false
-    if [[ -f $LOGFILE ]] && \
-    [[ $(grep -c "print" $LOGFILE) != 0 ]]; then
-        status=true
-    fi
-
-    if [ $status == false ]; then
-        echo "Response check failed, please check the logs in artifacts!"
-        exit 1
-    else
-        echo "Response check succeed!"
-    fi
-}
-
-if [ $# -eq 0 ]; then
-    echo "Usage: $0 <function_name>"
-    exit 1
-fi
-
-case "$1" in
-    init_CodeTrans)
-        pushd CodeTrans/kubernetes/intel/cpu/xeon/manifest
-        init_codetrans
-        popd
-        ;;
-    install_CodeTrans)
-        pushd CodeTrans/kubernetes/intel/cpu/xeon/manifest
-        NAMESPACE=$2
-        install_codetrans
-        popd
-        ;;
-    validate_CodeTrans)
-        NAMESPACE=$2
-        SERVICE_NAME=codetrans
-        validate_codetrans
-        ;;
-    *)
-        echo "Unknown function: $1"
-        ;;
-esac