From 0e5ab5ebfcba3613b6b9bc5805fbbd788ba4511d Mon Sep 17 00:00:00 2001 From: Shaojun Liu <61072813+liu-shaojun@users.noreply.github.com> Date: Mon, 13 Nov 2023 16:53:40 +0800 Subject: [PATCH] update docker tag to 2.5.0-SNAPSHOT (#9443) --- docker/llm/README.md | 34 +++++++++---------- docker/llm/finetune/lora/cpu/docker/README.md | 6 ++-- .../finetune/lora/cpu/kubernetes/values.yaml | 2 +- .../llm/finetune/qlora/xpu/docker/README.md | 8 ++--- docker/llm/inference/cpu/docker/README.md | 6 ++-- docker/llm/inference/xpu/docker/README.md | 4 +-- docker/llm/serving/cpu/docker/Dockerfile | 2 +- docker/llm/serving/cpu/docker/README.md | 4 +-- docker/llm/serving/cpu/kubernetes/README.md | 6 ++-- .../serving/cpu/kubernetes/deployment.yaml | 4 +-- docker/llm/serving/xpu/docker/Dockerfile | 2 +- docker/llm/serving/xpu/docker/README.md | 4 +-- 12 files changed, 41 insertions(+), 41 deletions(-) diff --git a/docker/llm/README.md b/docker/llm/README.md index 292e17d7..80e2f72f 100644 --- a/docker/llm/README.md +++ b/docker/llm/README.md @@ -27,11 +27,11 @@ The instructions for installing can be accessed from To pull image from hub, you can execute command on console: ```bash -docker pull intelanalytics/bigdl-llm-cpu:2.4.0-SNAPSHOT +docker pull intelanalytics/bigdl-llm-cpu:2.5.0-SNAPSHOT ``` to check if the image is successfully downloaded, you can use: ```powershell -docker images | sls intelanalytics/bigdl-llm-cpu:2.4.0-SNAPSHOT +docker images | sls intelanalytics/bigdl-llm-cpu:2.5.0-SNAPSHOT ``` @@ -42,7 +42,7 @@ To run the image and do inference, you could create and run a bat script on Wind An example on Windows could be: ```bat @echo off -set DOCKER_IMAGE=intelanalytics/bigdl-llm-cpu:2.4.0-SNAPSHOT +set DOCKER_IMAGE=intelanalytics/bigdl-llm-cpu:2.5.0-SNAPSHOT set CONTAINER_NAME=my_container set MODEL_PATH=D:/llm/models[change to your model path] @@ -112,7 +112,7 @@ Here is a demostration of how to use tutorial in explorer: To run container on Linux/MacOS: ```bash #/bin/bash -export DOCKER_IMAGE=intelanalytics/bigdl-llm-cpu:2.4.0-SNAPSHOT +export DOCKER_IMAGE=intelanalytics/bigdl-llm-cpu:2.5.0-SNAPSHOT export CONTAINER_NAME=my_container export MODEL_PATH=/llm/models[change to your model path] @@ -136,13 +136,13 @@ Also, you could use chat.py and bigdl-llm-tutorial for development. First, pull docker image from docker hub: ``` -docker pull intelanalytics/bigdl-llm-xpu:2.4.0-SNAPSHOT +docker pull intelanalytics/bigdl-llm-xpu:2.5.0-SNAPSHOT ``` To map the xpu into the container, you need to specify --device=/dev/dri when booting the container. An example could be: ```bash #/bin/bash -export DOCKER_IMAGE=intelanalytics/bigdl-llm-xpu:2.4.0-SNAPSHOT +export DOCKER_IMAGE=intelanalytics/bigdl-llm-xpu:2.5.0-SNAPSHOT export CONTAINER_NAME=my_container export MODEL_PATH=/llm/models[change to your model path] @@ -176,12 +176,12 @@ To run inference using `BigDL-LLM` using xpu, you could refer to this [documenta Pull image: ``` -docker pull intelanalytics/bigdl-llm-serving-cpu:2.4.0-SNAPSHOT +docker pull intelanalytics/bigdl-llm-serving-cpu:2.5.0-SNAPSHOT ``` You could use the following bash script to start the container. Please be noted that the CPU config is specified for Xeon CPUs, change it accordingly if you are not using a Xeon CPU. ```bash -export DOCKER_IMAGE=intelanalytics/bigdl-llm-serving-cpu:2.4.0-SNAPSHOT +export DOCKER_IMAGE=intelanalytics/bigdl-llm-serving-cpu:2.5.0-SNAPSHOT export CONTAINER_NAME=my_container export MODEL_PATH=/llm/models[change to your model path] @@ -268,7 +268,7 @@ python3 -m fastchat.serve.openai_api_server --host localhost --port 8000 Pull image: ``` -docker pull intelanalytics/bigdl-llm-serving-xpu:2.4.0-SNAPSHOT +docker pull intelanalytics/bigdl-llm-serving-xpu:2.5.0-SNAPSHOT ``` To map the `xpu` into the container, you need to specify `--device=/dev/dri` when booting the container. @@ -276,7 +276,7 @@ To map the `xpu` into the container, you need to specify `--device=/dev/dri` whe An example could be: ```bash #/bin/bash -export DOCKER_IMAGE=intelanalytics/bigdl-llm-serving-cpu:2.4.0-SNAPSHOT +export DOCKER_IMAGE=intelanalytics/bigdl-llm-serving-cpu:2.5.0-SNAPSHOT export CONTAINER_NAME=my_container export MODEL_PATH=/llm/models[change to your model path] export SERVICE_MODEL_PATH=/llm/models/chatglm2-6b[a specified model path for running service] @@ -362,7 +362,7 @@ python3 -m fastchat.serve.openai_api_server --host localhost --port 8000 You can download directly from Dockerhub like: ```bash -docker pull intelanalytics/bigdl-llm-finetune-lora-cpu:2.4.0-SNAPSHOT +docker pull intelanalytics/bigdl-llm-finetune-lora-cpu:2.5.0-SNAPSHOT ``` Or build the image from source: @@ -374,7 +374,7 @@ export HTTPS_PROXY=your_https_proxy docker build \ --build-arg http_proxy=${HTTP_PROXY} \ --build-arg https_proxy=${HTTPS_PROXY} \ - -t intelanalytics/bigdl-llm-finetune-lora-cpu:2.4.0-SNAPSHOT \ + -t intelanalytics/bigdl-llm-finetune-lora-cpu:2.5.0-SNAPSHOT \ -f ./Dockerfile . ``` @@ -390,7 +390,7 @@ docker run -itd \ -e WORKER_COUNT_DOCKER=your_worker_count \ -v your_downloaded_base_model_path:/bigdl/model \ -v your_downloaded_data_path:/bigdl/data/alpaca_data_cleaned_archive.json \ - intelanalytics/bigdl-llm-finetune-cpu:2.4.0-SNAPSHOT \ + intelanalytics/bigdl-llm-finetune-cpu:2.5.0-SNAPSHOT \ bash ``` @@ -449,7 +449,7 @@ The following shows how to fine-tune LLM with Quantization (QLoRA built on BigDL You can download directly from Dockerhub like: ```bash -docker pull intelanalytics/bigdl-llm-finetune-qlora-xpu:2.4.0-SNAPSHOT +docker pull intelanalytics/bigdl-llm-finetune-qlora-xpu:2.5.0-SNAPSHOT ``` Or build the image from source: @@ -461,7 +461,7 @@ export HTTPS_PROXY=your_https_proxy docker build \ --build-arg http_proxy=${HTTP_PROXY} \ --build-arg https_proxy=${HTTPS_PROXY} \ - -t intelanalytics/bigdl-llm-finetune-qlora-xpu:2.4.0-SNAPSHOT \ + -t intelanalytics/bigdl-llm-finetune-qlora-xpu:2.5.0-SNAPSHOT \ -f ./Dockerfile . ``` @@ -485,7 +485,7 @@ docker run -itd \ -v $BASE_MODE_PATH:/model \ -v $DATA_PATH:/data/english_quotes \ --shm-size="16g" \ - intelanalytics/bigdl-llm-fintune-qlora-xpu:2.4.0-SNAPSHOT + intelanalytics/bigdl-llm-fintune-qlora-xpu:2.5.0-SNAPSHOT ``` The download and mount of base model and data to a docker container demonstrates a standard fine-tuning process. You can skip this step for a quick start, and in this way, the fine-tuning codes will automatically download the needed files: @@ -502,7 +502,7 @@ docker run -itd \ -e http_proxy=${HTTP_PROXY} \ -e https_proxy=${HTTPS_PROXY} \ --shm-size="16g" \ - intelanalytics/bigdl-llm-fintune-qlora-xpu:2.4.0-SNAPSHOT + intelanalytics/bigdl-llm-fintune-qlora-xpu:2.5.0-SNAPSHOT ``` However, we do recommend you to handle them manually, because the automatical download can be blocked by Internet access and Huggingface authentication etc. according to different environment, and the manual method allows you to fine-tune in a custom way (with different base model and dataset). diff --git a/docker/llm/finetune/lora/cpu/docker/README.md b/docker/llm/finetune/lora/cpu/docker/README.md index 4578dda6..93013bc0 100644 --- a/docker/llm/finetune/lora/cpu/docker/README.md +++ b/docker/llm/finetune/lora/cpu/docker/README.md @@ -5,7 +5,7 @@ You can download directly from Dockerhub like: ```bash -docker pull intelanalytics/bigdl-llm-finetune-lora-cpu:2.4.0-SNAPSHOT +docker pull intelanalytics/bigdl-llm-finetune-lora-cpu:2.5.0-SNAPSHOT ``` Or build the image from source: @@ -17,7 +17,7 @@ export HTTPS_PROXY=your_https_proxy docker build \ --build-arg http_proxy=${HTTP_PROXY} \ --build-arg https_proxy=${HTTPS_PROXY} \ - -t intelanalytics/bigdl-llm-finetune-lora-cpu:2.4.0-SNAPSHOT \ + -t intelanalytics/bigdl-llm-finetune-lora-cpu:2.5.0-SNAPSHOT \ -f ./Dockerfile . ``` @@ -33,7 +33,7 @@ docker run -itd \ -e WORKER_COUNT_DOCKER=your_worker_count \ -v your_downloaded_base_model_path:/bigdl/model \ -v your_downloaded_data_path:/bigdl/data/alpaca_data_cleaned_archive.json \ - intelanalytics/bigdl-llm-finetune-lora-cpu:2.4.0-SNAPSHOT \ + intelanalytics/bigdl-llm-finetune-lora-cpu:2.5.0-SNAPSHOT \ bash ``` diff --git a/docker/llm/finetune/lora/cpu/kubernetes/values.yaml b/docker/llm/finetune/lora/cpu/kubernetes/values.yaml index 6c0e9ae7..36e137b8 100644 --- a/docker/llm/finetune/lora/cpu/kubernetes/values.yaml +++ b/docker/llm/finetune/lora/cpu/kubernetes/values.yaml @@ -1,4 +1,4 @@ -imageName: intelanalytics/bigdl-llm-finetune-lora-cpu:2.4.0-SNAPSHOT +imageName: intelanalytics/bigdl-llm-finetune-lora-cpu:2.5.0-SNAPSHOT trainerNum: 8 microBatchSize: 8 nfsServerIp: your_nfs_server_ip diff --git a/docker/llm/finetune/qlora/xpu/docker/README.md b/docker/llm/finetune/qlora/xpu/docker/README.md index 368fd52f..1371a513 100644 --- a/docker/llm/finetune/qlora/xpu/docker/README.md +++ b/docker/llm/finetune/qlora/xpu/docker/README.md @@ -7,7 +7,7 @@ The following shows how to fine-tune LLM with Quantization (QLoRA built on BigDL You can download directly from Dockerhub like: ```bash -docker pull intelanalytics/bigdl-llm-finetune-qlora-xpu:2.4.0-SNAPSHOT +docker pull intelanalytics/bigdl-llm-finetune-qlora-xpu:2.5.0-SNAPSHOT ``` Or build the image from source: @@ -19,7 +19,7 @@ export HTTPS_PROXY=your_https_proxy docker build \ --build-arg http_proxy=${HTTP_PROXY} \ --build-arg https_proxy=${HTTPS_PROXY} \ - -t intelanalytics/bigdl-llm-finetune-qlora-xpu:2.4.0-SNAPSHOT \ + -t intelanalytics/bigdl-llm-finetune-qlora-xpu:2.5.0-SNAPSHOT \ -f ./Dockerfile . ``` @@ -43,7 +43,7 @@ docker run -itd \ -v $BASE_MODE_PATH:/model \ -v $DATA_PATH:/data/english_quotes \ --shm-size="16g" \ - intelanalytics/bigdl-llm-fintune-qlora-xpu:2.4.0-SNAPSHOT + intelanalytics/bigdl-llm-fintune-qlora-xpu:2.5.0-SNAPSHOT ``` The download and mount of base model and data to a docker container demonstrates a standard fine-tuning process. You can skip this step for a quick start, and in this way, the fine-tuning codes will automatically download the needed files: @@ -60,7 +60,7 @@ docker run -itd \ -e http_proxy=${HTTP_PROXY} \ -e https_proxy=${HTTPS_PROXY} \ --shm-size="16g" \ - intelanalytics/bigdl-llm-fintune-qlora-xpu:2.4.0-SNAPSHOT + intelanalytics/bigdl-llm-fintune-qlora-xpu:2.5.0-SNAPSHOT ``` However, we do recommend you to handle them manually, because the automatical download can be blocked by Internet access and Huggingface authentication etc. according to different environment, and the manual method allows you to fine-tune in a custom way (with different base model and dataset). diff --git a/docker/llm/inference/cpu/docker/README.md b/docker/llm/inference/cpu/docker/README.md index 5111a37e..cbe6c8ae 100644 --- a/docker/llm/inference/cpu/docker/README.md +++ b/docker/llm/inference/cpu/docker/README.md @@ -6,7 +6,7 @@ docker build \ --build-arg http_proxy=.. \ --build-arg https_proxy=.. \ --build-arg no_proxy=.. \ - --rm --no-cache -t intelanalytics/bigdl-llm-cpu:2.4.0-SNAPSHOT . + --rm --no-cache -t intelanalytics/bigdl-llm-cpu:2.5.0-SNAPSHOT . ``` @@ -16,7 +16,7 @@ docker build \ An example could be: ```bash #/bin/bash -export DOCKER_IMAGE=intelanalytics/bigdl-llm-cpu:2.4.0-SNAPSHOT +export DOCKER_IMAGE=intelanalytics/bigdl-llm-cpu:2.5.0-SNAPSHOT sudo docker run -itd \ --net=host \ @@ -41,7 +41,7 @@ You can download models and bind the model directory from host machine to contai Here is an example: ```bash -export DOCKER_IMAGE=intelanalytics/bigdl-llm-cpu:2.4.0-SNAPSHOT +export DOCKER_IMAGE=intelanalytics/bigdl-llm-cpu:2.5.0-SNAPSHOT export MODEL_PATH=/home/llm/models sudo docker run -itd \ diff --git a/docker/llm/inference/xpu/docker/README.md b/docker/llm/inference/xpu/docker/README.md index 49fbdfba..32bbb277 100644 --- a/docker/llm/inference/xpu/docker/README.md +++ b/docker/llm/inference/xpu/docker/README.md @@ -6,7 +6,7 @@ docker build \ --build-arg http_proxy=.. \ --build-arg https_proxy=.. \ --build-arg no_proxy=.. \ - --rm --no-cache -t intelanalytics/bigdl-llm-xpu:2.4.0-SNAPSHOT . + --rm --no-cache -t intelanalytics/bigdl-llm-xpu:2.5.0-SNAPSHOT . ``` @@ -17,7 +17,7 @@ To map the `xpu` into the container, you need to specify `--device=/dev/dri` whe An example could be: ```bash #/bin/bash -export DOCKER_IMAGE=intelanalytics/bigdl-llm-xpu:2.4.0-SNAPSHOT +export DOCKER_IMAGE=intelanalytics/bigdl-llm-xpu:2.5.0-SNAPSHOT sudo docker run -itd \ --net=host \ diff --git a/docker/llm/serving/cpu/docker/Dockerfile b/docker/llm/serving/cpu/docker/Dockerfile index 1c829bb9..7edcc099 100644 --- a/docker/llm/serving/cpu/docker/Dockerfile +++ b/docker/llm/serving/cpu/docker/Dockerfile @@ -1,4 +1,4 @@ -FROM intelanalytics/bigdl-llm-cpu:2.4.0-SNAPSHOT +FROM intelanalytics/bigdl-llm-cpu:2.5.0-SNAPSHOT ARG http_proxy ARG https_proxy diff --git a/docker/llm/serving/cpu/docker/README.md b/docker/llm/serving/cpu/docker/README.md index 6024a859..84b156d1 100644 --- a/docker/llm/serving/cpu/docker/README.md +++ b/docker/llm/serving/cpu/docker/README.md @@ -6,7 +6,7 @@ docker build \ --build-arg http_proxy=.. \ --build-arg https_proxy=.. \ --build-arg no_proxy=.. \ - --rm --no-cache -t intelanalytics/bigdl-llm-serving-cpu:2.4.0-SNAPSHOT . + --rm --no-cache -t intelanalytics/bigdl-llm-serving-cpu:2.5.0-SNAPSHOT . ``` @@ -17,7 +17,7 @@ You could use the following bash script to start the container. Please be noted ```bash #/bin/bash -export DOCKER_IMAGE=intelanalytics/bigdl-llm-serving-cpu:2.4.0-SNAPSHOT +export DOCKER_IMAGE=intelanalytics/bigdl-llm-serving-cpu:2.5.0-SNAPSHOT sudo docker run -itd \ --net=host \ diff --git a/docker/llm/serving/cpu/kubernetes/README.md b/docker/llm/serving/cpu/kubernetes/README.md index d5394d29..5a11fa59 100644 --- a/docker/llm/serving/cpu/kubernetes/README.md +++ b/docker/llm/serving/cpu/kubernetes/README.md @@ -3,7 +3,7 @@ ## Image -To deploy BigDL-LLM-serving cpu in Kubernetes environment, please use this image: `intelanalytics/bigdl-llm-serving-cpu:2.4.0-SNAPSHOT` +To deploy BigDL-LLM-serving cpu in Kubernetes environment, please use this image: `intelanalytics/bigdl-llm-serving-cpu:2.5.0-SNAPSHOT` ## Before deployment @@ -48,7 +48,7 @@ spec: dnsPolicy: "ClusterFirst" containers: - name: fastchat-controller # fixed - image: intelanalytics/bigdl-llm-serving-cpu:2.4.0-SNAPSHOT + image: intelanalytics/bigdl-llm-serving-cpu:2.5.0-SNAPSHOT imagePullPolicy: IfNotPresent env: - name: CONTROLLER_HOST # fixed @@ -119,7 +119,7 @@ spec: dnsPolicy: "ClusterFirst" containers: - name: fastchat-worker # fixed - image: intelanalytics/bigdl-llm-serving-cpu:2.4.0-SNAPSHOT + image: intelanalytics/bigdl-llm-serving-cpu:2.5.0-SNAPSHOT imagePullPolicy: IfNotPresent env: - name: CONTROLLER_HOST # fixed diff --git a/docker/llm/serving/cpu/kubernetes/deployment.yaml b/docker/llm/serving/cpu/kubernetes/deployment.yaml index bd659fd4..4eacf285 100644 --- a/docker/llm/serving/cpu/kubernetes/deployment.yaml +++ b/docker/llm/serving/cpu/kubernetes/deployment.yaml @@ -9,7 +9,7 @@ spec: dnsPolicy: "ClusterFirst" containers: - name: fastchat-controller # fixed - image: intelanalytics/bigdl-llm-serving-cpu:2.4.0-SNAPSHOT + image: intelanalytics/bigdl-llm-serving-cpu:2.5.0-SNAPSHOT imagePullPolicy: IfNotPresent env: - name: CONTROLLER_HOST # fixed @@ -74,7 +74,7 @@ spec: dnsPolicy: "ClusterFirst" containers: - name: fastchat-worker # fixed - image: intelanalytics/bigdl-llm-serving-cpu:2.4.0-SNAPSHOT + image: intelanalytics/bigdl-llm-serving-cpu:2.5.0-SNAPSHOT imagePullPolicy: IfNotPresent env: - name: CONTROLLER_HOST # fixed diff --git a/docker/llm/serving/xpu/docker/Dockerfile b/docker/llm/serving/xpu/docker/Dockerfile index 829778d6..a8ad97d7 100644 --- a/docker/llm/serving/xpu/docker/Dockerfile +++ b/docker/llm/serving/xpu/docker/Dockerfile @@ -1,4 +1,4 @@ -FROM intelanalytics/bigdl-llm-xpu:2.4.0-SNAPSHOT +FROM intelanalytics/bigdl-llm-xpu:2.5.0-SNAPSHOT ARG http_proxy ARG https_proxy diff --git a/docker/llm/serving/xpu/docker/README.md b/docker/llm/serving/xpu/docker/README.md index 5a2dcd39..85b266bc 100644 --- a/docker/llm/serving/xpu/docker/README.md +++ b/docker/llm/serving/xpu/docker/README.md @@ -6,7 +6,7 @@ docker build \ --build-arg http_proxy=.. \ --build-arg https_proxy=.. \ --build-arg no_proxy=.. \ - --rm --no-cache -t intelanalytics/bigdl-llm-serving-xpu:2.4.0-SNAPSHOT . + --rm --no-cache -t intelanalytics/bigdl-llm-serving-xpu:2.5.0-SNAPSHOT . ``` @@ -18,7 +18,7 @@ To map the `xpu` into the container, you need to specify `--device=/dev/dri` whe An example could be: ```bash #/bin/bash -export DOCKER_IMAGE=intelanalytics/bigdl-llm-serving-xpu:2.4.0-SNAPSHOT +export DOCKER_IMAGE=intelanalytics/bigdl-llm-serving-xpu:2.5.0-SNAPSHOT sudo docker run -itd \ --net=host \