jandres/GenAIExamples
1
0
Fork 0
Code Issues Pull Requests Actions 3 Packages Projects Releases Wiki Activity

Make all xeon tgi image version consistent (#851)

Browse Source 
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
This commit is contained in:
Steve Zhang
2024-09-24 11:19:37 +08:00
committed by GitHub
parent 6f4b00f829
commit 954a22051b
10 changed files with 15 additions and 15 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
AudioQnA/kubernetes/intel/cpu/xeon/manifest/audioqna.yaml
View File

@@ -247,7 +247,7 @@ spec:
- envFrom:
- configMapRef:
name: audio-qna-config
image: ghcr.io/huggingface/text-generation-inference:2.2.0
image: "ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu"
name: llm-dependency-deploy-demo
securityContext:
capabilities:

4
ChatQnA/docker_compose/intel/cpu/xeon/README.md
View File

@@ -233,7 +233,7 @@ For users in China who are unable to download models directly from Huggingface,
export HF_TOKEN=${your_hf_token}
export HF_ENDPOINT="https://hf-mirror.com"
model_name="Intel/neural-chat-7b-v3-3"
docker run -p 8008:80 -v ./data:/data --name tgi-service -e HF_ENDPOINT=$HF_ENDPOINT -e http_proxy=$http_proxy -e https_proxy=$https_proxy --shm-size 1g ghcr.io/huggingface/text-generation-inference:2.2.0 --model-id $model_name
docker run -p 8008:80 -v ./data:/data --name tgi-service -e HF_ENDPOINT=$HF_ENDPOINT -e http_proxy=$http_proxy -e https_proxy=$https_proxy --shm-size 1g ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu --model-id $model_name
```
2. Offline
@@ -247,7 +247,7 @@ For users in China who are unable to download models directly from Huggingface,
```bash
export HF_TOKEN=${your_hf_token}
export model_path="/path/to/model"
docker run -p 8008:80 -v $model_path:/data --name tgi_service --shm-size 1g ghcr.io/huggingface/text-generation-inference:2.2.0 --model-id /data
docker run -p 8008:80 -v $model_path:/data --name tgi_service --shm-size 1g ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu --model-id /data
```
### Setup Environment Variables

4
ChatQnA/kubernetes/intel/cpu/xeon/manifest/chatqna-guardrails.yaml
View File

@@ -1474,7 +1474,7 @@ spec:
runAsUser: 1000
seccompProfile:
type: RuntimeDefault
image: "ghcr.io/huggingface/text-generation-inference:2.2.0"
image: "ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu"
imagePullPolicy: IfNotPresent
volumeMounts:
- mountPath: /data
@@ -1554,7 +1554,7 @@ spec:
runAsUser: 1000
seccompProfile:
type: RuntimeDefault
image: "ghcr.io/huggingface/text-generation-inference:2.2.0"
image: "ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu"
imagePullPolicy: IfNotPresent
volumeMounts:
- mountPath: /data

8
DocSum/kubernetes/intel/README_gmc.md
View File

@@ -7,9 +7,9 @@ Install GMC in your Kubernetes cluster, if you have not already done so, by foll
The DocSum application is defined as a Custom Resource (CR) file that the above GMC operator acts upon. It first checks if the microservices listed in the CR yaml file are running, if not it starts them and then proceeds to connect them. When the DocSum RAG pipeline is ready, the service endpoint details are returned, letting you use the application. Should you use "kubectl get pods" commands you will see all the component microservices, in particular embedding, retriever, rerank, and llm.
The DocSum pipeline uses prebuilt images. The Xeon version uses the prebuilt image llm-docsum-tgi:latest which internally leverages the
the image ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu. The service is called tgi-svc. Meanwhile, the Gaudi version launches the
service tgi-gaudi-svc, which uses the image `ghcr.io/huggingface/tgi-gaudi:2.0.5`. Both TGI model services serve the model specified in the LLM_MODEL_ID variable that is exported by you. In the below example we use Intel/neural-chat-7b-v3-3.
The DocSum pipeline uses prebuilt images. The Xeon version uses the prebuilt image `llm-docsum-tgi:latest` which internally leverages the
the image `ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu`. The service is called tgi-svc. Meanwhile, the Gaudi version launches the
service tgi-gaudi-svc, which uses the image `ghcr.io/huggingface/tgi-gaudi:2.0.5`. Both TGI model services serve the model specified in the LLM_MODEL_ID variable that is exported by you. In the below example we use `Intel/neural-chat-7b-v3-3`.
[NOTE]
Refer to [Docker Xeon README](https://github.com/opea-project/GenAIExamples/blob/main/DocSum/docker_compose/intel/cpu/xeon/README.md) or
@@ -17,7 +17,7 @@ Refer to [Docker Xeon README](https://github.com/opea-project/GenAIExamples/blob
These will be available on Docker Hub soon, simplifying installation.
## Deploy the RAG pipeline
This involves deploying the application pipeline custom resource. You can use docsum_xeon.yaml if you have just a Xeon cluster or docsum_gaudi.yaml if you have a Gaudi cluster.
This involves deploying the application pipeline custom resource. You can use `docsum_xeon.yaml` if you have just a Xeon cluster or `docsum_gaudi.yaml` if you have a Gaudi cluster.
1. Setup Environment variables. These are specific to the user. Skip the proxy settings if you are not operating behind one.

2
ProductivitySuite/kubernetes/intel/cpu/xeon/manifest/chatqna.yaml
View File

@@ -993,7 +993,7 @@ spec:
name: chatqna-tgi-config
securityContext:
{}
image: "ghcr.io/huggingface/text-generation-inference:2.1.0"
image: "ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu"
imagePullPolicy: IfNotPresent
volumeMounts:
- mountPath: /data

2
ProductivitySuite/kubernetes/intel/cpu/xeon/manifest/codegen.yaml
View File

@@ -229,7 +229,7 @@ spec:
name: codegen-tgi-config
securityContext:
{}
image: "ghcr.io/huggingface/text-generation-inference:1.4"
image: "ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu"
imagePullPolicy: IfNotPresent
volumeMounts:
- mountPath: /data

2
ProductivitySuite/kubernetes/intel/cpu/xeon/manifest/docsum.yaml
View File

@@ -229,7 +229,7 @@ spec:
name: docsum-tgi-config
securityContext:
{}
image: "ghcr.io/huggingface/text-generation-inference:2.1.0"
image: "ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu"
imagePullPolicy: IfNotPresent
volumeMounts:
- mountPath: /data

2
ProductivitySuite/kubernetes/intel/cpu/xeon/manifest/faqgen.yaml
View File

@@ -138,7 +138,7 @@ spec:
- configMapRef:
name: faqgen-tgi-config
securityContext: {}
image: "ghcr.io/huggingface/text-generation-inference:2.1.0"
image: "ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu"
imagePullPolicy: IfNotPresent
volumeMounts:
- mountPath: /data

2
VisualQnA/kubernetes/intel/cpu/xeon/manifest/visualqna.yaml
View File

@@ -216,7 +216,7 @@ spec:
name: visualqna-tgi-config
securityContext:
{}
image: "ghcr.io/huggingface/text-generation-inference:2.2.0"
image: "ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu"
imagePullPolicy: IfNotPresent
volumeMounts:
- mountPath: /data

2
VisualQnA/tests/test_compose_on_xeon.sh
View File

@@ -21,7 +21,7 @@ function build_docker_images() {
echo "Build all the images with --no-cache, check docker_image_build.log for details..."
docker compose -f build.yaml build --no-cache > ${LOG_PATH}/docker_image_build.log
docker pull ghcr.io/huggingface/text-generation-inference:2.2.0
docker pull ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu
docker images && sleep 1s
}