From 45833bfcbfbd843d96943a477952d9330673c78d Mon Sep 17 00:00:00 2001 From: ZePan110 Date: Tue, 19 Nov 2024 22:18:41 +0800 Subject: [PATCH] Rename image name XXX-hpu to XXX-gaudi (#1154) Signed-off-by: ZePan110 Signed-off-by: Chingis Yundunov --- .github/workflows/_example-workflow.yml | 2 +- ChatQnA/docker_compose/intel/hpu/gaudi/compose_vllm.yaml | 2 +- ChatQnA/docker_image_build/build.yaml | 4 ++-- ChatQnA/kubernetes/intel/hpu/gaudi/manifest/chatqna-vllm.yaml | 2 +- ChatQnA/tests/test_compose_vllm_on_gaudi.sh | 2 +- docker_images_list.md | 4 ++-- 6 files changed, 8 insertions(+), 8 deletions(-) diff --git a/.github/workflows/_example-workflow.yml b/.github/workflows/_example-workflow.yml index c7131aad26..a86ac25929 100644 --- a/.github/workflows/_example-workflow.yml +++ b/.github/workflows/_example-workflow.yml @@ -77,7 +77,7 @@ jobs: git clone https://github.com/vllm-project/vllm.git cd vllm && git rev-parse HEAD && cd ../ fi - if [[ $(grep -c "vllm-hpu:" ${docker_compose_path}) != 0 ]]; then + if [[ $(grep -c "vllm-gaudi:" ${docker_compose_path}) != 0 ]]; then git clone https://github.com/HabanaAI/vllm-fork.git cd vllm-fork && git checkout 3c39626 && cd ../ fi diff --git a/ChatQnA/docker_compose/intel/hpu/gaudi/compose_vllm.yaml b/ChatQnA/docker_compose/intel/hpu/gaudi/compose_vllm.yaml index d0d3433f1f..9b4002b5bf 100644 --- a/ChatQnA/docker_compose/intel/hpu/gaudi/compose_vllm.yaml +++ b/ChatQnA/docker_compose/intel/hpu/gaudi/compose_vllm.yaml @@ -78,7 +78,7 @@ services: MAX_WARMUP_SEQUENCE_LENGTH: 512 command: --model-id ${RERANK_MODEL_ID} --auto-truncate vllm-service: - image: ${REGISTRY:-opea}/vllm-hpu:${TAG:-latest} + image: ${REGISTRY:-opea}/vllm-gaudi:${TAG:-latest} container_name: vllm-gaudi-server ports: - "8007:80" diff --git a/ChatQnA/docker_image_build/build.yaml b/ChatQnA/docker_image_build/build.yaml index aab333ec8b..a8fa36bc3b 100644 --- a/ChatQnA/docker_image_build/build.yaml +++ b/ChatQnA/docker_image_build/build.yaml @@ -119,12 +119,12 @@ services: dockerfile: Dockerfile.cpu extends: chatqna image: ${REGISTRY:-opea}/vllm:${TAG:-latest} - vllm-hpu: + vllm-gaudi: build: context: vllm-fork dockerfile: Dockerfile.hpu extends: chatqna - image: ${REGISTRY:-opea}/vllm-hpu:${TAG:-latest} + image: ${REGISTRY:-opea}/vllm-gaudi:${TAG:-latest} nginx: build: context: GenAIComps diff --git a/ChatQnA/kubernetes/intel/hpu/gaudi/manifest/chatqna-vllm.yaml b/ChatQnA/kubernetes/intel/hpu/gaudi/manifest/chatqna-vllm.yaml index ec7a542264..715db8976f 100644 --- a/ChatQnA/kubernetes/intel/hpu/gaudi/manifest/chatqna-vllm.yaml +++ b/ChatQnA/kubernetes/intel/hpu/gaudi/manifest/chatqna-vllm.yaml @@ -1284,7 +1284,7 @@ spec: runAsUser: 1000 seccompProfile: type: RuntimeDefault - image: "opea/vllm-hpu:latest" + image: "opea/vllm-gaudi:latest" args: - "--enforce-eager" - "--model" diff --git a/ChatQnA/tests/test_compose_vllm_on_gaudi.sh b/ChatQnA/tests/test_compose_vllm_on_gaudi.sh index d7d8059d85..f261c519a6 100644 --- a/ChatQnA/tests/test_compose_vllm_on_gaudi.sh +++ b/ChatQnA/tests/test_compose_vllm_on_gaudi.sh @@ -20,7 +20,7 @@ function build_docker_images() { git clone https://github.com/HabanaAI/vllm-fork.git && cd vllm-fork && git checkout 3c39626 && cd ../ echo "Build all the images with --no-cache, check docker_image_build.log for details..." - service_list="chatqna chatqna-ui dataprep-redis retriever-redis vllm-hpu nginx" + service_list="chatqna chatqna-ui dataprep-redis retriever-redis vllm-gaudi nginx" 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 diff --git a/docker_images_list.md b/docker_images_list.md index ea25a906ea..9efea72ebe 100644 --- a/docker_images_list.md +++ b/docker_images_list.md @@ -78,7 +78,7 @@ Take ChatQnA for example. ChatQnA is a chatbot application service based on the | [opea/llm-tgi](https://hub.docker.com/r/opea/llm-tgi) | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/llms/text-generation/tgi/Dockerfile) | The docker image exposed the OPEA LLM microservice upon TGI docker image for GenAI application use | | [opea/llm-vllm](https://hub.docker.com/r/opea/llm-vllm) | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/llms/text-generation/vllm/langchain/Dockerfile) | The docker image exposed the OPEA LLM microservice upon vLLM docker image for GenAI application use | | [opea/llm-vllm-llamaindex](https://hub.docker.com/r/opea/llm-vllm-llamaindex) | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/llms/text-generation/vllm/llama_index/Dockerfile) | This docker image exposes OPEA LLM microservices to the llamaindex framework's vLLM Docker image for use by GenAI applications | -| [opea/llava-hpu](https://hub.docker.com/r/opea/llava-hpu) | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/lvms/llava/dependency/Dockerfile.intel_hpu) | The docker image exposed the OPEA microservice running LLaVA as a large visual model (LVM) service for GenAI application use on the Gaudi | +| [opea/llava-gaudi](https://hub.docker.com/r/opea/llava-hpu) | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/lvms/llava/dependency/Dockerfile.intel_hpu) | The docker image exposed the OPEA microservice running LLaVA as a large visual model (LVM) service for GenAI application use on the Gaudi | | [opea/lvm-tgi](https://hub.docker.com/r/opea/lvm-tgi) | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/lvms/tgi-llava/Dockerfile) | This docker image is designed to build a large visual model (LVM) microservice using the HuggingFace Text Generation Inference(TGI) framework. The microservice accepts document input and generates a answer to question. | | [opea/lvm-llava](https://hub.docker.com/r/opea/lvm-llava) | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/lvms/llava/dependency/Dockerfile) | The docker image exposed the OPEA microservice running LLaVA as a large visual model (LVM) server for GenAI application use | | [opea/lvm-llava-svc](https://hub.docker.com/r/opea/lvm-llava-svc) | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/lvms/llava/Dockerfile) | The docker image exposed the OPEA microservice running LLaVA as a large visual model (LVM) service for GenAI application use | @@ -106,7 +106,7 @@ Take ChatQnA for example. ChatQnA is a chatbot application service based on the | [opea/video-llama-lvm-server](https://hub.docker.com/r/opea/video-llama-lvm-server) | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/lvms/video-llama/dependency/Dockerfile) | The docker image exposed the OPEA microservice running Video-Llama as a large visual model (LVM) server for GenAI application use | | [opea/tts](https://hub.docker.com/r/opea/tts) | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/tts/speecht5/Dockerfile) | The docker image exposed the OPEA Text-To-Speech microservice for GenAI application use | | [opea/vllm](https://hub.docker.com/r/opea/vllm) | [Link](https://github.com/vllm-project/vllm/blob/main/Dockerfile.cpu) | The docker image powered by vllm-project for deploying and serving vllm Models | -| [opea/vllm-hpu]() | [Link](https://github.com/HabanaAI/vllm-fork/blob/habana_main/Dockerfile.hpu) | The docker image powered by vllm-fork for deploying and serving vllm-hpu Models | +| [opea/vllm-gaudi]() | [Link](https://github.com/HabanaAI/vllm-fork/blob/habana_main/Dockerfile.hpu) | The docker image powered by vllm-fork for deploying and serving vllm-gaudi Models | | [opea/vllm-openvino](https://hub.docker.com/r/opea/vllm-openvino) | [Link](https://github.com/vllm-project/vllm/blob/main/Dockerfile.openvino) | The docker image powered by vllm-project for deploying and serving vllm Models of the Openvino Framework | | [opea/web-retriever-chroma](https://hub.docker.com/r/opea/web-retriever-chroma) | [Link](https://github.com/opea-project/GenAIComps/tree/main/comps/web_retrievers/chroma/langchain/Dockerfile) | The docker image exposed the OPEA retrieval microservice based on chroma vectordb for GenAI application use | | [opea/whisper](https://hub.docker.com/r/opea/whisper) | [Link](https://github.com/opea-project/GenAIComps/blob/main/comps/asr/whisper/dependency/Dockerfile) | The docker image exposed the OPEA Whisper service for GenAI application use |