Address comments

Signed-off-by: Dolpher Du <[email protected]>
opea-project · Jan 9, 2025 · e19ecf2 · e19ecf2
1 parent dd560d5
commit e19ecf2
Show file tree

Hide file tree

Showing 4 changed files with 7 additions and 10 deletions.
diff --git a/comps/3rd_parties/tgi/deployment/kubernetes/README.md b/comps/3rd_parties/tgi/deployment/kubernetes/README.md
@@ -1,7 +1,7 @@
-# Deploy tgi on kubernetes cluster
+# Deploy TGI on kubernetes cluster
 
 - You should have Helm (version >= 3.15) installed. Refer to the [Helm Installation Guide](https://helm.sh/docs/intro/install/) for more information.
-- For more deploy options, refer to [helm charts README](https://github.com/opea-project/GenAIInfra/tree/main/helm-charts#readme).
+- For more deployment options, refer to [helm charts README](https://github.com/opea-project/GenAIInfra/tree/main/helm-charts#readme).
 
 ## Deploy on Xeon
 

diff --git a/comps/3rd_parties/tgi/deployment/kubernetes/cpu-values.yaml b/comps/3rd_parties/tgi/deployment/kubernetes/cpu-values.yaml
@@ -1,8 +1,6 @@
 # Copyright (C) 2024 Intel Corporation
 # SPDX-License-Identifier: Apache-2.0
 
-LLM_MODEL_ID: Intel/neural-chat-7b-v3-3
-
 # Resource requirements for Intel/neural-chat-7b-v3-3 @ 32-bit:
 resources:
   limits:

diff --git a/comps/3rd_parties/tgi/deployment/kubernetes/gaudi-values.yaml b/comps/3rd_parties/tgi/deployment/kubernetes/gaudi-values.yaml
@@ -1,10 +1,6 @@
 # Copyright (C) 2024 Intel Corporation
 # SPDX-License-Identifier: Apache-2.0
 
-# Default values for tgi.
-# This is a YAML-formatted file.
-# Declare variables to be passed into your templates.
-
 accelDevice: "gaudi"
 
 image:
@@ -23,6 +19,9 @@ FLASH_ATTENTION_RECOMPUTE: "true"
 resources:
   limits:
     habana.ai/gaudi: 1
+  requests:
+    cpu: 1
+    memory: 16Gi
 
 livenessProbe:
   initialDelaySeconds: 5

diff --git a/comps/llms/deployment/kubernetes/README.md b/comps/llms/deployment/kubernetes/README.md
@@ -1,7 +1,7 @@
-# Deploy llm microservice on Kubernetes cluster
+# Deploy LLM microservice on Kubernetes cluster
 
 - You should have Helm (version >= 3.15) installed. Refer to the [Helm Installation Guide](https://helm.sh/docs/intro/install/) for more information.
-- For more deploy options, refer to [helm charts README](https://github.com/opea-project/GenAIInfra/tree/main/helm-charts#readme).
+- For more deployment options, refer to [helm charts README](https://github.com/opea-project/GenAIInfra/tree/main/helm-charts#readme).
 
 ## Deploy on Kubernetes