From a8543d9da5c67406b796cd8bc20fd2605305facb Mon Sep 17 00:00:00 2001 From: Sihan Chen <39623753+Spycsh@users.noreply.github.com> Date: Wed, 21 Aug 2024 22:17:07 +0800 Subject: [PATCH] fix tgi xeon tag (#641) --- AudioQnA/docker/xeon/compose.yaml | 2 +- ChatQnA/docker/xeon/compose.yaml | 2 +- ChatQnA/docker/xeon/compose_qdrant.yaml | 2 +- ChatQnA/kubernetes/README.md | 2 +- ChatQnA/kubernetes/manifests/xeon/chatqna.yaml | 2 +- CodeGen/docker/xeon/compose.yaml | 2 +- CodeGen/kubernetes/manifests/xeon/codegen.yaml | 2 +- CodeGen/kubernetes/manifests/xeon/ui/react-codegen.yaml | 2 +- CodeGen/tests/test_codegen_on_xeon.sh | 2 +- CodeTrans/docker/xeon/compose.yaml | 2 +- CodeTrans/kubernetes/manifests/xeon/codetrans.yaml | 2 +- DocSum/docker/xeon/compose.yaml | 2 +- DocSum/kubernetes/README.md | 2 +- DocSum/kubernetes/manifests/xeon/docsum.yaml | 2 +- DocSum/kubernetes/manifests/xeon/ui/react-docsum.yaml | 2 +- FaqGen/docker/xeon/compose.yaml | 2 +- FaqGen/kubernetes/manifests/xeon/ui/react-faqgen.yaml | 2 +- SearchQnA/docker/xeon/compose.yaml | 2 +- SearchQnA/tests/test_searchqna_on_xeon.sh | 2 +- Translation/docker/xeon/compose.yaml | 2 +- VisualQnA/docker/xeon/README.md | 4 ++-- VisualQnA/docker/xeon/compose.yaml | 2 +- 22 files changed, 23 insertions(+), 23 deletions(-) diff --git a/AudioQnA/docker/xeon/compose.yaml b/AudioQnA/docker/xeon/compose.yaml index f640ecae37..a0ef81d172 100644 --- a/AudioQnA/docker/xeon/compose.yaml +++ b/AudioQnA/docker/xeon/compose.yaml @@ -41,7 +41,7 @@ services: environment: TTS_ENDPOINT: ${TTS_ENDPOINT} tgi-service: - image: ghcr.io/huggingface/text-generation-inference:latest-intel-cpu + image: ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu container_name: tgi-service ports: - "3006:80" diff --git a/ChatQnA/docker/xeon/compose.yaml b/ChatQnA/docker/xeon/compose.yaml index 3828aa57fd..4697300a7d 100644 --- a/ChatQnA/docker/xeon/compose.yaml +++ b/ChatQnA/docker/xeon/compose.yaml @@ -102,7 +102,7 @@ services: HF_HUB_ENABLE_HF_TRANSFER: 0 restart: unless-stopped tgi-service: - image: ghcr.io/huggingface/text-generation-inference:latest-intel-cpu + image: ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu container_name: tgi-service ports: - "9009:80" diff --git a/ChatQnA/docker/xeon/compose_qdrant.yaml b/ChatQnA/docker/xeon/compose_qdrant.yaml index a149d94266..922f74dcfb 100644 --- a/ChatQnA/docker/xeon/compose_qdrant.yaml +++ b/ChatQnA/docker/xeon/compose_qdrant.yaml @@ -102,7 +102,7 @@ services: HF_HUB_ENABLE_HF_TRANSFER: 0 restart: unless-stopped tgi-service: - image: ghcr.io/huggingface/text-generation-inference:latest-intel-cpu + image: ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu container_name: tgi-service ports: - "6042:80" diff --git a/ChatQnA/kubernetes/README.md b/ChatQnA/kubernetes/README.md index 55be039436..c666e9fae5 100644 --- a/ChatQnA/kubernetes/README.md +++ b/ChatQnA/kubernetes/README.md @@ -20,7 +20,7 @@ The ChatQnA uses the below prebuilt images if you choose a Xeon deployment - retriever: opea/retriever-redis:latest - tei_xeon_service: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5 - reranking: opea/reranking-tei:latest -- tgi-service: ghcr.io/huggingface/text-generation-inference:latest-intel-cpu +- tgi-service: ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu - llm: opea/llm-tgi:latest - chaqna-xeon-backend-server: opea/chatqna:latest diff --git a/ChatQnA/kubernetes/manifests/xeon/chatqna.yaml b/ChatQnA/kubernetes/manifests/xeon/chatqna.yaml index 022ddfa4c6..cf5070d94b 100644 --- a/ChatQnA/kubernetes/manifests/xeon/chatqna.yaml +++ b/ChatQnA/kubernetes/manifests/xeon/chatqna.yaml @@ -1121,7 +1121,7 @@ spec: name: chatqna-tgi-config securityContext: {} - image: "ghcr.io/huggingface/text-generation-inference:latest-intel-cpu" + image: "ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu" imagePullPolicy: IfNotPresent volumeMounts: - mountPath: /data diff --git a/CodeGen/docker/xeon/compose.yaml b/CodeGen/docker/xeon/compose.yaml index ba7bcdabfb..ab1e4150ce 100644 --- a/CodeGen/docker/xeon/compose.yaml +++ b/CodeGen/docker/xeon/compose.yaml @@ -3,7 +3,7 @@ services: tgi-service: - image: ghcr.io/huggingface/text-generation-inference:latest-intel-cpu + image: ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu container_name: tgi-service ports: - "8028:80" diff --git a/CodeGen/kubernetes/manifests/xeon/codegen.yaml b/CodeGen/kubernetes/manifests/xeon/codegen.yaml index 9b5729dd0c..55fbc6ffbe 100644 --- a/CodeGen/kubernetes/manifests/xeon/codegen.yaml +++ b/CodeGen/kubernetes/manifests/xeon/codegen.yaml @@ -239,7 +239,7 @@ spec: name: codegen-tgi-config securityContext: {} - image: "ghcr.io/huggingface/text-generation-inference:latest-intel-cpu" + image: "ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu" imagePullPolicy: IfNotPresent volumeMounts: - mountPath: /data diff --git a/CodeGen/kubernetes/manifests/xeon/ui/react-codegen.yaml b/CodeGen/kubernetes/manifests/xeon/ui/react-codegen.yaml index ac21f68357..5d77fb8cc8 100644 --- a/CodeGen/kubernetes/manifests/xeon/ui/react-codegen.yaml +++ b/CodeGen/kubernetes/manifests/xeon/ui/react-codegen.yaml @@ -126,7 +126,7 @@ spec: - name: no_proxy value: securityContext: {} - image: "ghcr.io/huggingface/text-generation-inference:latest-intel-cpu" + image: "ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu" imagePullPolicy: IfNotPresent volumeMounts: - mountPath: /data diff --git a/CodeGen/tests/test_codegen_on_xeon.sh b/CodeGen/tests/test_codegen_on_xeon.sh index 6e759dc4ec..19259d6a6c 100644 --- a/CodeGen/tests/test_codegen_on_xeon.sh +++ b/CodeGen/tests/test_codegen_on_xeon.sh @@ -22,7 +22,7 @@ function build_docker_images() { service_list="codegen codegen-ui llm-tgi" docker compose -f docker_build_compose.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log - docker pull ghcr.io/huggingface/text-generation-inference:latest-intel-cpu + docker pull ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu docker images } diff --git a/CodeTrans/docker/xeon/compose.yaml b/CodeTrans/docker/xeon/compose.yaml index c4666621c1..e62989122b 100644 --- a/CodeTrans/docker/xeon/compose.yaml +++ b/CodeTrans/docker/xeon/compose.yaml @@ -3,7 +3,7 @@ services: tgi-service: - image: ghcr.io/huggingface/text-generation-inference:latest-intel-cpu + image: ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu container_name: codetrans-tgi-service ports: - "8008:80" diff --git a/CodeTrans/kubernetes/manifests/xeon/codetrans.yaml b/CodeTrans/kubernetes/manifests/xeon/codetrans.yaml index 76d6fbfcbf..e3b66e6b13 100644 --- a/CodeTrans/kubernetes/manifests/xeon/codetrans.yaml +++ b/CodeTrans/kubernetes/manifests/xeon/codetrans.yaml @@ -239,7 +239,7 @@ spec: name: codetrans-tgi-config securityContext: {} - image: "ghcr.io/huggingface/text-generation-inference:latest-intel-cpu" + image: "ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu" imagePullPolicy: IfNotPresent volumeMounts: - mountPath: /data diff --git a/DocSum/docker/xeon/compose.yaml b/DocSum/docker/xeon/compose.yaml index ffb2ba7f56..620ee36575 100644 --- a/DocSum/docker/xeon/compose.yaml +++ b/DocSum/docker/xeon/compose.yaml @@ -3,7 +3,7 @@ services: tgi-service: - image: ghcr.io/huggingface/text-generation-inference:latest-intel-cpu + image: ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu container_name: tgi-service ports: - "8008:80" diff --git a/DocSum/kubernetes/README.md b/DocSum/kubernetes/README.md index 6627f8cb7e..c91f0fccb5 100644 --- a/DocSum/kubernetes/README.md +++ b/DocSum/kubernetes/README.md @@ -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:latest-intel-cpu. The service is called tgi-svc. Meanwhile, the Gaudi version launches 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:1.2.1. 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] diff --git a/DocSum/kubernetes/manifests/xeon/docsum.yaml b/DocSum/kubernetes/manifests/xeon/docsum.yaml index 06a73e07c7..77f38b6ab6 100644 --- a/DocSum/kubernetes/manifests/xeon/docsum.yaml +++ b/DocSum/kubernetes/manifests/xeon/docsum.yaml @@ -239,7 +239,7 @@ spec: name: docsum-tgi-config securityContext: {} - image: "ghcr.io/huggingface/text-generation-inference:latest-intel-cpu" + image: "ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu" imagePullPolicy: IfNotPresent volumeMounts: - mountPath: /data diff --git a/DocSum/kubernetes/manifests/xeon/ui/react-docsum.yaml b/DocSum/kubernetes/manifests/xeon/ui/react-docsum.yaml index 4f902a22a1..61e8799b0e 100644 --- a/DocSum/kubernetes/manifests/xeon/ui/react-docsum.yaml +++ b/DocSum/kubernetes/manifests/xeon/ui/react-docsum.yaml @@ -126,7 +126,7 @@ spec: - name: no_proxy value: securityContext: {} - image: "ghcr.io/huggingface/text-generation-inference:latest-intel-cpu" + image: "ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu" imagePullPolicy: IfNotPresent volumeMounts: - mountPath: /data diff --git a/FaqGen/docker/xeon/compose.yaml b/FaqGen/docker/xeon/compose.yaml index d5d955984c..8c5c894aed 100644 --- a/FaqGen/docker/xeon/compose.yaml +++ b/FaqGen/docker/xeon/compose.yaml @@ -3,7 +3,7 @@ services: tgi-service: - image: ghcr.io/huggingface/text-generation-inference:latest-intel-cpu + image: ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu container_name: tgi-xeon-server ports: - "8008:80" diff --git a/FaqGen/kubernetes/manifests/xeon/ui/react-faqgen.yaml b/FaqGen/kubernetes/manifests/xeon/ui/react-faqgen.yaml index bfb3be0b08..845ba50412 100644 --- a/FaqGen/kubernetes/manifests/xeon/ui/react-faqgen.yaml +++ b/FaqGen/kubernetes/manifests/xeon/ui/react-faqgen.yaml @@ -126,7 +126,7 @@ spec: - name: no_proxy value: securityContext: {} - image: "ghcr.io/huggingface/text-generation-inference:latest-intel-cpu" + image: "ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu" imagePullPolicy: IfNotPresent volumeMounts: - mountPath: /data diff --git a/SearchQnA/docker/xeon/compose.yaml b/SearchQnA/docker/xeon/compose.yaml index 4dcf9b9239..380eddb307 100644 --- a/SearchQnA/docker/xeon/compose.yaml +++ b/SearchQnA/docker/xeon/compose.yaml @@ -73,7 +73,7 @@ services: HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN} restart: unless-stopped tgi-service: - image: ghcr.io/huggingface/text-generation-inference:latest-intel-cpu + image: ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu container_name: tgi-service ports: - "3006:80" diff --git a/SearchQnA/tests/test_searchqna_on_xeon.sh b/SearchQnA/tests/test_searchqna_on_xeon.sh index 8c083dc9a7..03255f4a12 100644 --- a/SearchQnA/tests/test_searchqna_on_xeon.sh +++ b/SearchQnA/tests/test_searchqna_on_xeon.sh @@ -23,7 +23,7 @@ function build_docker_images() { docker compose -f docker_build_compose.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:latest-intel-cpu + docker pull ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu docker images } diff --git a/Translation/docker/xeon/compose.yaml b/Translation/docker/xeon/compose.yaml index 1ca7cee9dd..4ba224bf35 100644 --- a/Translation/docker/xeon/compose.yaml +++ b/Translation/docker/xeon/compose.yaml @@ -3,7 +3,7 @@ services: tgi-service: - image: ghcr.io/huggingface/text-generation-inference:latest-intel-cpu + image: ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu container_name: tgi-service ports: - "8008:80" diff --git a/VisualQnA/docker/xeon/README.md b/VisualQnA/docker/xeon/README.md index 346f3bc4e7..7cf245e80a 100644 --- a/VisualQnA/docker/xeon/README.md +++ b/VisualQnA/docker/xeon/README.md @@ -73,12 +73,12 @@ cd ../../../.. ### 4. Pull TGI Xeon Image ```bash -docker pull ghcr.io/huggingface/text-generation-inference:latest-intel-cpu +docker pull ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu ``` Then run the command `docker images`, you will have the following 4 Docker Images: -1. `ghcr.io/huggingface/text-generation-inference:latest-intel-cpu` +1. `ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu` 2. `opea/lvm-tgi:latest` 3. `opea/visualqna:latest` 4. `opea/visualqna-ui:latest` diff --git a/VisualQnA/docker/xeon/compose.yaml b/VisualQnA/docker/xeon/compose.yaml index 6bb9206b43..1fafa24ec6 100644 --- a/VisualQnA/docker/xeon/compose.yaml +++ b/VisualQnA/docker/xeon/compose.yaml @@ -3,7 +3,7 @@ services: llava-tgi-service: - image: ghcr.io/huggingface/text-generation-inference:latest-intel-cpu + image: ghcr.io/huggingface/text-generation-inference:sha-e4201f4-intel-cpu container_name: tgi-llava-xeon-server ports: - "9399:80"