added more cases

ChatQnA/benchmark/performance/helm_charts/oob_four_gaudi_with_rerank.yaml

@@ -0,0 +1,24 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+podSpecs:
+  - name: chatqna-backend-server-deploy
+    replicas: 4
+
+  - name: embedding-dependency-deploy
+    replicas: 4
+
+  - name: reranking-dependency-deploy
+    replicas: 1
+
+  - name: llm-dependency-deploy
+    replicas: 63
+
+  - name: dataprep-deploy
+    replicas: 1
+
+  - name: vector-db
+    replicas: 1
+
+  - name: retriever-deploy
+    replicas: 4

ChatQnA/benchmark/performance/helm_charts/oob_four_gaudi_without_rerank.yaml

@@ -0,0 +1,21 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+podSpecs:
+  - name: chatqna-backend-server-deploy
+    replicas: 4
+
+  - name: embedding-dependency-deploy
+    replicas: 4
+
+  - name: llm-dependency-deploy
+    replicas: 63
+
+  - name: dataprep-deploy
+    replicas: 1
+
+  - name: vector-db
+    replicas: 1
+
+  - name: retriever-deploy
+    replicas: 4

ChatQnA/benchmark/performance/helm_charts/oob_single_gaudi_with_rerank.yaml

@@ -0,0 +1,24 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+podSpecs:
+  - name: chatqna-backend-server-deploy
+    replicas: 2
+
+  - name: embedding-dependency-deploy
+    replicas: 2
+
+  - name: reranking-dependency-deploy
+    replicas: 1
+
+  - name: llm-dependency-deploy
+    replicas: 15
+
+  - name: dataprep-deploy
+    replicas: 1
+
+  - name: vector-db
+    replicas: 1
+
+  - name: retriever-deploy
+    replicas: 2

ChatQnA/benchmark/performance/helm_charts/oob_single_gaudi_without_rerank.yaml

@@ -0,0 +1,21 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+podSpecs:
+  - name: chatqna-backend-server-deploy
+    replicas: 2
+
+  - name: embedding-dependency-deploy
+    replicas: 2
+
+  - name: llm-dependency-deploy
+    replicas: 16
+
+  - name: dataprep-deploy
+    replicas: 1
+
+  - name: vector-db
+    replicas: 1
+
+  - name: retriever-deploy
+    replicas: 2

ChatQnA/benchmark/performance/helm_charts/oob_two_gaudi_with_rerank.yaml

@@ -0,0 +1,24 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+podSpecs:
+  - name: chatqna-backend-server-deploy
+    replicas: 2
+
+  - name: embedding-dependency-deploy
+    replicas: 2
+
+  - name: reranking-dependency-deploy
+    replicas: 1
+
+  - name: llm-dependency-deploy
+    replicas: 31
+
+  - name: dataprep-deploy
+    replicas: 1
+
+  - name: vector-db
+    replicas: 1
+
+  - name: retriever-deploy
+    replicas: 2

ChatQnA/benchmark/performance/helm_charts/oob_two_gaudi_without_rerank.yaml

@@ -0,0 +1,21 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+podSpecs:
+  - name: chatqna-backend-server-deploy
+    replicas: 2
+
+  - name: embedding-dependency-deploy
+    replicas: 2
+
+  - name: llm-dependency-deploy
+    replicas: 32
+
+  - name: dataprep-deploy
+    replicas: 1
+
+  - name: vector-db
+    replicas: 1
+
+  - name: retriever-deploy
+    replicas: 2

ChatQnA/benchmark/performance/helm_charts/tuned_four_gaudi_with_rerank.yaml

@@ -0,0 +1,48 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+podSpecs:
+  - name: chatqna-backend-server-deploy
+    replicas: 4
+    resources:
+      limits:
+        cpu: "16"
+        memory: "8000Mi"
+      requests:
+        cpu: "16"
+        memory: "8000Mi"
+
+  - name: embedding-dependency-deploy
+    replicas: 4
+    resources:
+      limits:
+        cpu: "80"
+        memory: "20000Mi"
+      requests:
+        cpu: "80"
+        memory: "20000Mi"
+
+  - name: reranking-dependency-deploy
+    replicas: 1
+    resources:
+      limits:
+        habana.ai/gaudi: 1
+
+  - name: llm-dependency-deploy
+    replicas: 63
+    resources:
+      limits:
+        habana.ai/gaudi: 1
+
+  - name: dataprep-deploy
+    replicas: 1
+
+  - name: vector-db
+    replicas: 1
+
+  - name: retriever-deploy
+    replicas: 4
+    resources:
+      requests:
+        cpu: "16"
+        memory: "4000Mi"

ChatQnA/benchmark/performance/helm_charts/tuned_four_gaudi_without_rerank.yaml

@@ -0,0 +1,42 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+podSpecs:
+  - name: chatqna-backend-server-deploy
+    replicas: 4
+    resources:
+      limits:
+        cpu: "16"
+        memory: "8000Mi"
+      requests:
+        cpu: "16"
+        memory: "8000Mi"
+
+  - name: embedding-dependency-deploy
+    replicas: 4
+    resources:
+      limits:
+        cpu: "80"
+        memory: "20000Mi"
+      requests:
+        cpu: "80"
+        memory: "20000Mi"
+
+  - name: llm-dependency-deploy
+    replicas: 64
+    resources:
+      limits:
+        habana.ai/gaudi: 1
+
+  - name: dataprep-deploy
+    replicas: 1
+
+  - name: vector-db
+    replicas: 1
+
+  - name: retriever-deploy
+    replicas: 4
+    resources:
+      requests:
+        cpu: "16"
+        memory: "4000Mi"

ChatQnA/benchmark/performance/helm_charts/tuned_single_gaudi_with_rerank.yaml

@@ -0,0 +1,48 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+podSpecs:
+  - name: chatqna-backend-server-deploy
+    replicas: 2
+    resources:
+      limits:
+        cpu: "16"
+        memory: "8000Mi"
+      requests:
+        cpu: "16"
+        memory: "8000Mi"
+
+  - name: embedding-dependency-deploy
+    replicas: 1
+    resources:
+      limits:
+        cpu: "80"
+        memory: "20000Mi"
+      requests:
+        cpu: "80"
+        memory: "20000Mi"
+
+  - name: reranking-dependency-deploy
+    replicas: 1
+    resources:
+      limits:
+        habana.ai/gaudi: 1
+
+  - name: llm-dependency-deploy
+    replicas: 7
+    resources:
+      limits:
+        habana.ai/gaudi: 1
+
+  - name: dataprep-deploy
+    replicas: 1
+
+  - name: vector-db
+    replicas: 1
+
+  - name: retriever-deploy
+    replicas: 2
+    resources:
+      requests:
+        cpu: "16"
+        memory: "4000Mi"

ChatQnA/benchmark/performance/helm_charts/tuned_single_gaudi_without_rerank.yaml

@@ -0,0 +1,42 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+podSpecs:
+  - name: chatqna-backend-server-deploy
+    replicas: 2
+    resources:
+      limits:
+        cpu: "16"
+        memory: "8000Mi"
+      requests:
+        cpu: "16"
+        memory: "8000Mi"
+
+  - name: embedding-dependency-deploy
+    replicas: 1
+    resources:
+      limits:
+        cpu: "80"
+        memory: "20000Mi"
+      requests:
+        cpu: "80"
+        memory: "20000Mi"
+
+  - name: llm-dependency-deploy
+    replicas: 8
+    resources:
+      limits:
+        habana.ai/gaudi: 1
+
+  - name: dataprep-deploy
+    replicas: 1
+
+  - name: vector-db
+    replicas: 1
+
+  - name: retriever-deploy
+    replicas: 2
+    resources:
+      requests:
+        cpu: "16"
+        memory: "4000Mi"

ChatQnA/benchmark/performance/helm_charts/tuned_two_gaudi_with_rerank.yaml

@@ -0,0 +1,48 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+podSpecs:
+  - name: chatqna-backend-server-deploy
+    replicas: 2
+    resources:
+      limits:
+        cpu: "16"
+        memory: "8000Mi"
+      requests:
+        cpu: "16"
+        memory: "8000Mi"
+
+  - name: embedding-dependency-deploy
+    replicas: 2
+    resources:
+      limits:
+        cpu: "80"
+        memory: "20000Mi"
+      requests:
+        cpu: "80"
+        memory: "20000Mi"
+
+  - name: reranking-dependency-deploy
+    replicas: 1
+    resources:
+      limits:
+        habana.ai/gaudi: 1
+
+  - name: llm-dependency-deploy
+    replicas: 15
+    resources:
+      limits:
+        habana.ai/gaudi: 1
+
+  - name: dataprep-deploy
+    replicas: 1
+
+  - name: vector-db
+    replicas: 1
+
+  - name: retriever-deploy
+    replicas: 2
+    resources:
+      requests:
+        cpu: "16"
+        memory: "4000Mi"

ChatQnA/benchmark/performance/helm_charts/tuned_two_gaudi_without_rerank.yaml

@@ -0,0 +1,42 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+podSpecs:
+  - name: chatqna-backend-server-deploy
+    replicas: 2
+    resources:
+      limits:
+        cpu: "16"
+        memory: "8000Mi"
+      requests:
+        cpu: "16"
+        memory: "8000Mi"
+
+  - name: embedding-dependency-deploy
+    replicas: 2
+    resources:
+      limits:
+        cpu: "80"
+        memory: "20000Mi"
+      requests:
+        cpu: "80"
+        memory: "20000Mi"
+
+  - name: llm-dependency-deploy
+    replicas: 16
+    resources:
+      limits:
+        habana.ai/gaudi: 1
+
+  - name: dataprep-deploy
+    replicas: 1
+
+  - name: vector-db
+    replicas: 1
+
+  - name: retriever-deploy
+    replicas: 2
+    resources:
+      requests:
+        cpu: "16"
+        memory: "4000Mi"