From 3563f5db6be91100a10c2f070fed28820a34ca0c Mon Sep 17 00:00:00 2001
From: Zhenzhong1 <109137058+Zhenzhong1@users.noreply.github.com>
Date: Tue, 3 Sep 2024 15:24:54 +0800
Subject: [PATCH] [ChatQnA]Update manifests (#716)

* update manifests for v0.9
---
 ChatQnA/benchmark/four_gaudi/chatqna_config_map.yaml   | 2 +-
 ChatQnA/benchmark/four_gaudi/llm-dependency_run.yaml   | 4 ++--
 ChatQnA/benchmark/single_gaudi/llm-dependency_run.yaml | 4 ++--
 ChatQnA/benchmark/two_gaudi/llm-dependency_run.yaml    | 4 ++--
 4 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/ChatQnA/benchmark/four_gaudi/chatqna_config_map.yaml b/ChatQnA/benchmark/four_gaudi/chatqna_config_map.yaml
index 24b8e72df..368c800e4 100644
--- a/ChatQnA/benchmark/four_gaudi/chatqna_config_map.yaml
+++ b/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
diff --git a/ChatQnA/benchmark/four_gaudi/llm-dependency_run.yaml b/ChatQnA/benchmark/four_gaudi/llm-dependency_run.yaml
index 130089f87..127160e33 100644
--- a/ChatQnA/benchmark/four_gaudi/llm-dependency_run.yaml
+++ b/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
diff --git a/ChatQnA/benchmark/single_gaudi/llm-dependency_run.yaml b/ChatQnA/benchmark/single_gaudi/llm-dependency_run.yaml
index 093d2264b..ae30c6a21 100644
--- a/ChatQnA/benchmark/single_gaudi/llm-dependency_run.yaml
+++ b/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
diff --git a/ChatQnA/benchmark/two_gaudi/llm-dependency_run.yaml b/ChatQnA/benchmark/two_gaudi/llm-dependency_run.yaml
index 9499f04ed..4d9988441 100644
--- a/ChatQnA/benchmark/two_gaudi/llm-dependency_run.yaml
+++ b/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