[ChatQnA]Update manifests (#716)

* update manifests for v0.9

ChatQnA/benchmark/four_gaudi/chatqna_config_map.yaml

@@ -15,7 +15,7 @@ data:
   TGI_LLM_ENDPOINT: http://llm-dependency-svc.default.svc.cluster.local:9009
   REDIS_URL: redis://vector-db.default.svc.cluster.local:6379
   INDEX_NAME: rag-redis
-  HUGGINGFACEHUB_API_TOKEN: {HF_TOKEN}
+  HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
   EMBEDDING_SERVICE_HOST_IP: embedding-svc
   RETRIEVER_SERVICE_HOST_IP: retriever-svc
   RERANK_SERVICE_HOST_IP: reranking-svc

ChatQnA/benchmark/four_gaudi/llm-dependency_run.yaml

@@ -35,9 +35,9 @@ spec:
         - --model-id
         - $(LLM_MODEL_ID)
         - --max-input-length
-        - '2048'
+        - '1024'
         - --max-total-tokens
-        - '4096'
+        - '2048'
         - --max-batch-total-tokens
         - '65536'
         - --max-batch-prefill-tokens

ChatQnA/benchmark/single_gaudi/llm-dependency_run.yaml

@@ -35,9 +35,9 @@ spec:
         - --model-id
         - $(LLM_MODEL_ID)
         - --max-input-length
-        - '2048'
+        - '1024'
         - --max-total-tokens
-        - '4096'
+        - '2048'
         - --max-batch-total-tokens
         - '65536'
         - --max-batch-prefill-tokens

ChatQnA/benchmark/two_gaudi/llm-dependency_run.yaml

@@ -35,9 +35,9 @@ spec:
         - --model-id
         - $(LLM_MODEL_ID)
         - --max-input-length
-        - '2048'
+        - '1024'
         - --max-total-tokens
-        - '4096'
+        - '2048'
         - --max-batch-total-tokens
         - '65536'
         - --max-batch-prefill-tokens