ayo/ipex-llm
1
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 1

replace 2.5.0-SNAPSHOT with 2.1.0-SNAPSHOT for llm docker images (#10603)

Browse source
This commit is contained in:
Shaojun Liu 2024-04-01 09:58:51 +08:00 committed by GitHub
parent 437a349dd6
commit 59058bb206
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
10 changed files with 23 additions and 23 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

6
docker/llm/finetune/lora/cpu/docker/README.md
View file

@ -5,7 +5,7 @@
You can download directly from Dockerhub like:
```bash
docker pull intelanalytics/ipex-llm-finetune-lora-cpu:2.5.0-SNAPSHOT
docker pull intelanalytics/ipex-llm-finetune-lora-cpu:2.1.0-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/ipex-llm-finetune-lora-cpu:2.5.0-SNAPSHOT \
-t intelanalytics/ipex-llm-finetune-lora-cpu:2.1.0-SNAPSHOT \
-f ./Dockerfile .
```
@ -33,7 +33,7 @@ docker run -itd \
-e WORKER_COUNT_DOCKER=your_worker_count \
-v your_downloaded_base_model_path:/ipex_llm/model \
-v your_downloaded_data_path:/ipex_llm/data/alpaca_data_cleaned_archive.json \
intelanalytics/ipex-llm-finetune-lora-cpu:2.5.0-SNAPSHOT \
intelanalytics/ipex-llm-finetune-lora-cpu:2.1.0-SNAPSHOT \
bash
```

2
docker/llm/finetune/lora/cpu/kubernetes/values.yaml
View file

@ -1,4 +1,4 @@
imageName: intelanalytics/ipex-llm-finetune-lora-cpu:2.5.0-SNAPSHOT
imageName: intelanalytics/ipex-llm-finetune-lora-cpu:2.1.0-SNAPSHOT
trainerNum: 8
microBatchSize: 8
nfsServerIp: your_nfs_server_ip

8
docker/llm/finetune/qlora/xpu/docker/README.md
View file

@ -7,7 +7,7 @@ The following shows how to fine-tune LLM with Quantization (QLoRA built on IPEX-
You can download directly from Dockerhub like:
```bash
docker pull intelanalytics/ipex-llm-finetune-qlora-xpu:2.5.0-SNAPSHOT
docker pull intelanalytics/ipex-llm-finetune-qlora-xpu:2.1.0-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/ipex-llm-finetune-qlora-xpu:2.5.0-SNAPSHOT \
-t intelanalytics/ipex-llm-finetune-qlora-xpu:2.1.0-SNAPSHOT \
-f ./Dockerfile .
```
@ -43,7 +43,7 @@ docker run -itd \
-v $BASE_MODE_PATH:/model \
-v $DATA_PATH:/data/alpaca-cleaned \
--shm-size="16g" \
intelanalytics/ipex-llm-fintune-qlora-xpu:2.5.0-SNAPSHOT
intelanalytics/ipex-llm-fintune-qlora-xpu:2.1.0-SNAPSHOT
```
The download and mount of base model and data to a docker container demonstrates a standard fine-tuning process. You can skip this step for a quick start, and in this way, the fine-tuning codes will automatically download the needed files:
@ -60,7 +60,7 @@ docker run -itd \
-e http_proxy=${HTTP_PROXY} \
-e https_proxy=${HTTPS_PROXY} \
--shm-size="16g" \
intelanalytics/ipex-llm-fintune-qlora-xpu:2.5.0-SNAPSHOT
intelanalytics/ipex-llm-fintune-qlora-xpu:2.1.0-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).

2
docker/llm/serving/cpu/docker/Dockerfile
View file

@ -1,4 +1,4 @@
FROM intelanalytics/ipex-llm-cpu:2.5.0-SNAPSHOT
FROM intelanalytics/ipex-llm-cpu:2.1.0-SNAPSHOT
ARG http_proxy
ARG https_proxy

8
docker/llm/serving/cpu/docker/README.md
View file

@ -6,7 +6,7 @@ docker build \
--build-arg http_proxy=.. \
--build-arg https_proxy=.. \
--build-arg no_proxy=.. \
--rm --no-cache -t intelanalytics/ipex-llm-serving-cpu:2.5.0-SNAPSHOT .
--rm --no-cache -t intelanalytics/ipex-llm-serving-cpu:2.1.0-SNAPSHOT .
```
### Use the image for doing cpu serving
@ -16,7 +16,7 @@ You could use the following bash script to start the container. Please be noted
```bash
#/bin/bash
export DOCKER_IMAGE=intelanalytics/ipex-llm-serving-cpu:2.5.0-SNAPSHOT
export DOCKER_IMAGE=intelanalytics/ipex-llm-serving-cpu:2.1.0-SNAPSHOT
sudo docker run -itd \
--net=host \
@ -36,7 +36,7 @@ Also you can set environment variables and start arguments while running a conta
To start a controller container:
```bash
#/bin/bash
export DOCKER_IMAGE=intelanalytics/ipex-llm-serving-cpu:2.5.0-SNAPSHOT
export DOCKER_IMAGE=intelanalytics/ipex-llm-serving-cpu:2.1.0-SNAPSHOT
controller_host=localhost
controller_port=23000
api_host=localhost
@ -59,7 +59,7 @@ sudo docker run -itd \
To start a worker container:
```bash
#/bin/bash
export DOCKER_IMAGE=intelanalytics/ipex-llm-serving-cpu:2.5.0-SNAPSHOT
export DOCKER_IMAGE=intelanalytics/ipex-llm-serving-cpu:2.1.0-SNAPSHOT
export MODEL_PATH=YOUR_MODEL_PATH
controller_host=localhost
controller_port=23000

6
docker/llm/serving/cpu/kubernetes/README.md
View file

@ -2,7 +2,7 @@
## Image
To deploy IPEX-LLM-serving cpu in Kubernetes environment, please use this image: `intelanalytics/ipex-llm-serving-cpu:2.5.0-SNAPSHOT`
To deploy IPEX-LLM-serving cpu in Kubernetes environment, please use this image: `intelanalytics/ipex-llm-serving-cpu:2.1.0-SNAPSHOT`
## Before deployment
@ -73,7 +73,7 @@ spec:
dnsPolicy: "ClusterFirst"
containers:
- name: fastchat-controller # fixed
image: intelanalytics/ipex-llm-serving-cpu:2.5.0-SNAPSHOT
image: intelanalytics/ipex-llm-serving-cpu:2.1.0-SNAPSHOT
imagePullPolicy: IfNotPresent
env:
- name: CONTROLLER_HOST # fixed
@ -146,7 +146,7 @@ spec:
dnsPolicy: "ClusterFirst"
containers:
- name: fastchat-worker # fixed
image: intelanalytics/ipex-llm-serving-cpu:2.5.0-SNAPSHOT
image: intelanalytics/ipex-llm-serving-cpu:2.1.0-SNAPSHOT
imagePullPolicy: IfNotPresent
env:
- name: CONTROLLER_HOST # fixed

4
docker/llm/serving/cpu/kubernetes/deployment.yaml
View file

@ -24,7 +24,7 @@ spec:
dnsPolicy: "ClusterFirst"
containers:
- name: fastchat-controller # fixed
image: intelanalytics/ipex-llm-serving-cpu:2.5.0-SNAPSHOT
image: intelanalytics/ipex-llm-serving-cpu:2.1.0-SNAPSHOT
imagePullPolicy: IfNotPresent
env:
- name: CONTROLLER_HOST # fixed
@ -91,7 +91,7 @@ spec:
dnsPolicy: "ClusterFirst"
containers:
- name: fastchat-worker # fixed
image: intelanalytics/ipex-llm-serving-cpu:2.5.0-SNAPSHOT
image: intelanalytics/ipex-llm-serving-cpu:2.1.0-SNAPSHOT
imagePullPolicy: IfNotPresent
env:
- name: CONTROLLER_HOST # fixed

2
docker/llm/serving/xpu/docker/Dockerfile
View file

@ -1,4 +1,4 @@
FROM intelanalytics/ipex-llm-xpu:2.5.0-SNAPSHOT
FROM intelanalytics/ipex-llm-xpu:2.1.0-SNAPSHOT
ARG http_proxy
ARG https_proxy

4
docker/llm/serving/xpu/docker/README.md
View file

@ -6,7 +6,7 @@ docker build \
--build-arg http_proxy=.. \
--build-arg https_proxy=.. \
--build-arg no_proxy=.. \
--rm --no-cache -t intelanalytics/ipex-llm-serving-xpu:2.5.0-SNAPSHOT .
--rm --no-cache -t intelanalytics/ipex-llm-serving-xpu:2.1.0-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/ipex-llm-serving-xpu:2.5.0-SNAPSHOT
export DOCKER_IMAGE=intelanalytics/ipex-llm-serving-xpu:2.1.0-SNAPSHOT
sudo docker run -itd \
--net=host \

4
docs/readthedocs/source/doc/LLM/Quickstart/docker_windows_gpu.md
View file

@ -55,7 +55,7 @@ It applies to Intel Core Core 12 - 14 gen integrated GPUs (iGPUs) and Intel Arc
### 1. Prepare ipex-llm-xpu Docker Image
Run the following command in WSL:
```bash
docker pull intelanalytics/ipex-llm-xpu:2.5.0-SNAPSHOT
docker pull intelanalytics/ipex-llm-xpu:2.1.0-SNAPSHOT
```
This step will take around 20 minutes depending on your network.
@ -64,7 +64,7 @@ This step will take around 20 minutes depending on your network.
To map the xpu into the container, an example (docker_setup.sh) could be:
```bash
#/bin/bash
export DOCKER_IMAGE=intelanalytics/ipex-llm-xpu:2.5.0-SNAPSHOT
export DOCKER_IMAGE=intelanalytics/ipex-llm-xpu:2.1.0-SNAPSHOT
export CONTAINER_NAME=my_container
export MODEL_PATH=/llm/models[change to your model path]