jandres/GenAIExamples
1
0
Fork 0
Code Issues Pull Requests Actions 5 Packages Projects Releases Wiki Activity

Update TGI CPU image to latest official release 2.4.0 (#1035)

Browse Source 
Signed-off-by: lvliang-intel <liang1.lv@intel.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
This commit is contained in:
lvliang-intel
2024-11-04 11:28:43 +08:00
committed by GitHub
parent 3372b9d480
commit 0306c620b5
40 changed files with 49 additions and 49 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
AudioQnA/docker_compose/intel/cpu/xeon/compose.yaml
View File

@@ -41,7 +41,7 @@ services:
environment:
TTS_ENDPOINT: ${TTS_ENDPOINT}
tgi-service:
image: ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu
image: ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu
container_name: tgi-service
ports:
- "3006:80"

2
AudioQnA/docker_compose/intel/cpu/xeon/compose_multilang.yaml
View File

@@ -26,7 +26,7 @@ services:
https_proxy: ${https_proxy}
restart: unless-stopped
tgi-service:
image: ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu
image: ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu
container_name: tgi-service
ports:
- "3006:80"

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:sha-e4201f4-intel-cpu"
image: "ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu"
name: llm-dependency-deploy-demo
securityContext:
capabilities:

2
AvatarChatbot/docker_compose/intel/cpu/xeon/compose.yaml
View File

@@ -42,7 +42,7 @@ services:
environment:
TTS_ENDPOINT: ${TTS_ENDPOINT}
tgi-service:
image: ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu
image: ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu
container_name: tgi-service
ports:
- "3006:80"

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

@@ -195,7 +195,7 @@ 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:sha-e4201f4-intel-cpu --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:2.4.0-intel-cpu --model-id $model_name
```
2. Offline
@@ -209,7 +209,7 @@ For users in China who are unable to download models directly from Huggingface,
```bash
export HF_TOKEN=${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:sha-e4201f4-intel-cpu --model-id /data
docker run -p 8008:80 -v $model_path:/data --name tgi_service --shm-size 1g ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu --model-id /data
```
### Setup Environment Variables

2
ChatQnA/docker_compose/intel/cpu/xeon/compose.yaml
View File

@@ -73,7 +73,7 @@ services:
HF_HUB_ENABLE_HF_TRANSFER: 0
command: --model-id ${RERANK_MODEL_ID} --auto-truncate
tgi-service:
image: ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu
image: ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu
container_name: tgi-service
ports:
- "9009:80"

2
ChatQnA/docker_compose/intel/cpu/xeon/compose_qdrant.yaml
View File

@@ -72,7 +72,7 @@ services:
HF_HUB_ENABLE_HF_TRANSFER: 0
command: --model-id ${RERANK_MODEL_ID} --auto-truncate
tgi-service:
image: ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu
image: ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu
container_name: tgi-service
ports:
- "6042:80"

2
ChatQnA/docker_compose/intel/cpu/xeon/compose_without_rerank.yaml
View File

@@ -57,7 +57,7 @@ services:
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
restart: unless-stopped
tgi-service:
image: ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu
image: ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu
container_name: tgi-service
ports:
- "9009:80"

2
ChatQnA/kubernetes/intel/README_gmc.md
View File

@@ -18,7 +18,7 @@ The ChatQnA uses the below prebuilt images if you choose a Xeon deployment
- tei_embedding_service: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
- retriever: opea/retriever-redis:latest
- tei_xeon_service: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
- tgi-service: ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu
- tgi-service: ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu
- chaqna-xeon-backend-server: opea/chatqna:latest
Should you desire to use the Gaudi accelerator, two alternate images are used for the embedding and llm services.

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

@@ -1100,7 +1100,7 @@ spec:
runAsUser: 1000
seccompProfile:
type: RuntimeDefault
image: "ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu"
image: "ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu"
imagePullPolicy: IfNotPresent
volumeMounts:
- mountPath: /data
@@ -1180,7 +1180,7 @@ spec:
runAsUser: 1000
seccompProfile:
type: RuntimeDefault
image: "ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu"
image: "ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu"
imagePullPolicy: IfNotPresent
volumeMounts:
- mountPath: /data

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

@@ -922,7 +922,7 @@ spec:
runAsUser: 1000
seccompProfile:
type: RuntimeDefault
image: "ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu"
image: "ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu"
imagePullPolicy: IfNotPresent
volumeMounts:
- mountPath: /data

2
ChatQnA/kubernetes/intel/cpu/xeon/manifest/chatqna_bf16.yaml
View File

@@ -925,7 +925,7 @@ spec:
runAsUser: 1000
seccompProfile:
type: RuntimeDefault
image: "ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu"
image: "ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu"
imagePullPolicy: IfNotPresent
volumeMounts:
- mountPath: /data

2
ChatQnA/tests/test_compose_on_xeon.sh
View File

@@ -22,7 +22,7 @@ function build_docker_images() {
service_list="chatqna chatqna-ui chatqna-conversation-ui dataprep-redis retriever-redis nginx"
docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log
docker pull ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu
docker pull ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu
docker pull ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
docker images && sleep 1s

2
CodeGen/docker_compose/intel/cpu/xeon/compose.yaml
View File

@@ -3,7 +3,7 @@
services:
tgi-service:
image: ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu
image: ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu
container_name: tgi-service
ports:
- "8028:80"

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

@@ -404,7 +404,7 @@ spec:
runAsUser: 1000
seccompProfile:
type: RuntimeDefault
image: "ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu"
image: "ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu"
imagePullPolicy: IfNotPresent
volumeMounts:
- mountPath: /data

2
CodeGen/kubernetes/intel/cpu/xeon/manifest/codegen_react_ui.yaml
View File

@@ -126,7 +126,7 @@ spec:
- name: no_proxy
value:
securityContext: {}
image: "ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu"
image: "ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu"
imagePullPolicy: IfNotPresent
volumeMounts:
- mountPath: /data

2
CodeGen/tests/test_compose_on_xeon.sh
View File

@@ -22,7 +22,7 @@ function build_docker_images() {
service_list="codegen codegen-ui llm-tgi"
docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log
docker pull ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu
docker pull ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu
docker images && sleep 1s
}

2
CodeTrans/docker_compose/intel/cpu/xeon/compose.yaml
View File

@@ -3,7 +3,7 @@
services:
tgi-service:
image: ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu
image: ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu
container_name: codetrans-tgi-service
ports:
- "8008:80"

2
CodeTrans/kubernetes/intel/cpu/xeon/manifest/codetrans.yaml
View File

@@ -404,7 +404,7 @@ spec:
runAsUser: 1000
seccompProfile:
type: RuntimeDefault
image: "ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu"
image: "ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu"
imagePullPolicy: IfNotPresent
volumeMounts:
- mountPath: /data

2
CodeTrans/tests/test_compose_on_xeon.sh
View File

@@ -22,7 +22,7 @@ function build_docker_images() {
service_list="codetrans codetrans-ui llm-tgi nginx"
docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log
docker pull ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu
docker pull ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu
docker images && sleep 1s
}

2
DocSum/docker_compose/intel/cpu/xeon/compose.yaml
View File

@@ -3,7 +3,7 @@
services:
tgi-service:
image: ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu
image: ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu
container_name: tgi-service
ports:
- "8008:80"

2
DocSum/kubernetes/intel/README_gmc.md
View File

@@ -8,7 +8,7 @@ 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
the image `ghcr.io/huggingface/text-generation-inference:2.4.0-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]

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

@@ -404,7 +404,7 @@ spec:
runAsUser: 1000
seccompProfile:
type: RuntimeDefault
image: "ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu"
image: "ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu"
imagePullPolicy: IfNotPresent
volumeMounts:
- mountPath: /data

2
DocSum/kubernetes/intel/cpu/xeon/manifest/ui/react-docsum.yaml
View File

@@ -126,7 +126,7 @@ spec:
- name: no_proxy
value:
securityContext: {}
image: "ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu"
image: "ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu"
imagePullPolicy: IfNotPresent
volumeMounts:
- mountPath: /data

2
FaqGen/docker_compose/intel/cpu/xeon/compose.yaml
View File

@@ -3,7 +3,7 @@
services:
tgi-service:
image: ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu
image: ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu
container_name: tgi-xeon-server
ports:
- "8008:80"

2
FaqGen/kubernetes/intel/cpu/xeon/manifest/faqgen_react_ui.yaml
View File

@@ -126,7 +126,7 @@ spec:
- name: no_proxy
value:
securityContext: {}
image: "ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu"
image: "ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu"
imagePullPolicy: IfNotPresent
volumeMounts:
- mountPath: /data

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:sha-e4201f4-intel-cpu"
image: "ghcr.io/huggingface/text-generation-inference:2.4.0-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:sha-e4201f4-intel-cpu"
image: "ghcr.io/huggingface/text-generation-inference:2.4.0-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:sha-e4201f4-intel-cpu"
image: "ghcr.io/huggingface/text-generation-inference:2.4.0-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:sha-e4201f4-intel-cpu"
image: "ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu"
imagePullPolicy: IfNotPresent
volumeMounts:
- mountPath: /data

2
SearchQnA/docker_compose/intel/cpu/xeon/compose.yaml
View File

@@ -73,7 +73,7 @@ services:
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
restart: unless-stopped
tgi-service:
image: ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu
image: ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu
container_name: tgi-service
ports:
- "3006:80"

2
SearchQnA/tests/test_compose_on_xeon.sh
View File

@@ -23,7 +23,7 @@ function build_docker_images() {
docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log
docker pull ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
docker pull ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu
docker pull ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu
docker images && sleep 1s
}

2
Translation/docker_compose/intel/cpu/xeon/compose.yaml
View File

@@ -3,7 +3,7 @@
services:
tgi-service:
image: ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu
image: ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu
container_name: tgi-service
ports:
- "8008:80"

2
Translation/kubernetes/intel/cpu/xeon/manifest/translation.yaml
View File

@@ -361,7 +361,7 @@ spec:
runAsUser: 1000
seccompProfile:
type: RuntimeDefault
image: "ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu"
image: "ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu"
imagePullPolicy: IfNotPresent
volumeMounts:
- mountPath: /data

2
Translation/tests/test_compose_on_xeon.sh
View File

@@ -22,7 +22,7 @@ function build_docker_images() {
service_list="translation translation-ui llm-tgi nginx"
docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log
docker pull ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu
docker pull ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu
docker images && sleep 1s
}

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

@@ -67,12 +67,12 @@ docker build --no-cache -t opea/visualqna-ui:latest --build-arg https_proxy=$htt
### 4. Pull TGI Xeon Image
```bash
docker pull ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu
docker pull ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu
```
Then run the command `docker images`, you will have the following 5 Docker Images:
1. `ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu`
1. `ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu`
2. `opea/lvm-tgi:latest`
3. `opea/visualqna:latest`
4. `opea/visualqna-ui:latest`

2
VisualQnA/docker_compose/intel/cpu/xeon/compose.yaml
View File

@@ -3,7 +3,7 @@
services:
llava-tgi-service:
image: ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu
image: ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu
container_name: tgi-llava-xeon-server
ports:
- "8399:80"

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:sha-e4201f4-intel-cpu"
image: "ghcr.io/huggingface/text-generation-inference:2.4.0-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:sha-e4201f4-intel-cpu
docker pull ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu
docker images && sleep 1s
}

14
VisualQnA/ui/svelte/package.json
View File

@@ -15,8 +15,7 @@
"@fortawesome/free-solid-svg-icons": "6.2.0",
"@playwright/test": "^1.33.0",
"@sveltejs/adapter-auto": "1.0.0-next.75",
"@sveltejs/adapter-static": "^3.0.0",
"@sveltejs/kit": "^2.0.0",
"@sveltejs/kit": "^1.30.4",
"@tailwindcss/typography": "0.5.7",
"@types/debug": "4.1.7",
"@types/node": "^20.12.13",
@@ -29,20 +28,21 @@
"eslint": "^8.16.0",
"eslint-config-prettier": "^8.3.0",
"eslint-plugin-neverthrow": "1.1.4",
"eslint-plugin-svelte3": "^4.0.0",
"postcss": "^8.4.31",
"postcss-load-config": "^4.0.1",
"postcss-preset-env": "^8.3.2",
"prettier": "^2.8.8",
"prettier-plugin-svelte": "^2.7.0",
"prettier-plugin-tailwindcss": "^0.3.0",
"svelte": "^4.0.0",
"svelte-check": "^3.0.0",
"svelte": "^3.59.1",
"svelte-check": "^2.7.1",
"svelte-fa": "3.0.3",
"svelte-preprocess": "^6.0.2",
"svelte-preprocess": "^4.10.7",
"tailwindcss": "^3.1.5",
"tslib": "^2.3.1",
"typescript": "^5.0.0",
"vite": "^5.0.0"
"typescript": "^4.7.4",
"vite": "^4.5.2"
},
"type": "module",
"dependencies": {