merge main branch

.github/workflows/workflow_finetune.yml

@@ -19,30 +19,44 @@ jobs:
         model: [ EleutherAI/gpt-j-6b, meta-llama/Llama-2-7b-chat-hf, gpt2, bigscience/bloom-560m, facebook/opt-125m, mosaicml/mpt-7b-chat, huggyllama/llama-7b ]
         isPR:
           - ${{inputs.ci_type == 'pr'}}
-        
+
         exclude:
           - { isPR: true }
         include:
           - { model: "EleutherAI/gpt-j-6b"}
           - { model: "meta-llama/Llama-2-7b-chat-hf"}
 
     runs-on: self-hosted
+
+    defaults:
+      run:
+        shell: bash
+    container:
+      image: ${{ vars.ACTIONS_RUNNER_CONTAINER_IMAGE }}
+      env:
+        http_proxy: ${{ vars.HTTP_PROXY_CONTAINER }}
+        https_proxy: ${{ vars.HTTPS_PROXY_CONTAINER }}
+      volumes:
+        - /var/run/docker.sock:/var/run/docker.sock
+        - ${{ vars.ACTIONS_RUNNER_CONFIG_PATH }}:/root/actions-runner-config
+
     steps:
       - name: Checkout
         uses: actions/checkout@v2
 
       - name: Load environment variables
-        run: cat ~/llm-ray-actions-runner/.env >> $GITHUB_ENV
+        run: cat /root/actions-runner-config/.env >> $GITHUB_ENV
 
       - name: Build Docker Image
-        run: docker build ./ --build-arg CACHEBUST=1 --build-arg http_proxy=${{ vars.HTTP_PROXY_IMAGE_BUILD }} --build-arg https_proxy=${{ vars.HTTPS_PROXY_IMAGE_BUILD }} -f dev/docker/Dockerfile.cpu_and_deepspeed -t finetune:latest && yes | docker container prune && yes | docker image prune
+        run: |
+          docker build ./ --build-arg CACHEBUST=1 --build-arg http_proxy=${{ vars.HTTP_PROXY_CONTAINER }} --build-arg https_proxy=${{ vars.HTTPS_PROXY_CONTAINER }} -f dev/docker/Dockerfile.cpu_and_deepspeed -t finetune:latest && yes | docker container prune && yes
+          docker image prune -f
 
       - name: Start Docker Container
         run: |
           cid=$(docker ps -q --filter "name=finetune")
           if [[ ! -z "$cid" ]]; then docker stop $cid && docker rm $cid; fi
-          docker run -tid -v /mnt/DP_disk1/huggingface/cache/:/root/.cache/huggingface/hub -v .:/root/llm-ray -e http_proxy=${{ vars.HTTP_PROXY_CONTAINER_RUN }} -e https_proxy=${{ vars.HTTPS_PROXY_CONTAINER_RUN }} --name="finetune" --hostname="finetune-container" finetune:latest
-
+          docker run -tid -v ${{ vars.MODEL_CACHE_PATH }}:/root/.cache/huggingface/hub -v ${{ vars.CODE_CHECKOUT_PATH }}:/root/llm-on-ray -e http_proxy=${{ vars.HTTP_PROXY_CONTAINER }} -e https_proxy=${{ vars.HTTPS_PROXY_CONTAINER }} --name="finetune" --hostname="finetune-container" finetune:latest
       - name: Run Finetune Test
         run: |
           docker exec "finetune" bash -c "source \$(python -c 'import oneccl_bindings_for_pytorch as torch_ccl;print(torch_ccl.cwd)')/env/setvars.sh; RAY_SERVE_ENABLE_EXPERIMENTAL_STREAMING=1 ray start --head --node-ip-address 127.0.0.1 --ray-debugger-external; RAY_SERVE_ENABLE_EXPERIMENTAL_STREAMING=1  ray start --address='127.0.0.1:6379' --ray-debugger-external"
@@ -129,7 +143,6 @@ jobs:
             docker exec "finetune" python -c "$CMD"
             docker exec "finetune" bash -c "python finetune/finetune.py --config_file finetune/finetune.yaml"
           fi
-
       - name: Stop Ray
         run: |
           cid=$(docker ps -q --filter "name=finetune")
@@ -142,6 +155,5 @@ jobs:
         run: |
           cid=$(docker ps -q --filter "name=finetune")
           if [[ ! -z "$cid" ]]; then docker stop $cid && docker rm $cid; fi
-
       - name: Test Summary
         run: echo "to be continued"

.github/workflows/workflow_finetune_gpu.yml

@@ -10,16 +10,27 @@ jobs:
       matrix:
         model: [ pythia-6.9b, gpt-j-6b ]
     runs-on: self-hosted
+
+    defaults:
+      run:
+        shell: bash
+    container:
+      image: ${{ vars.ACTIONS_RUNNER_CONTAINER_IMAGE }}
+      env:
+        http_proxy: ${{ vars.HTTP_PROXY_CONTAINER }}
+        https_proxy: ${{ vars.HTTPS_PROXY_CONTAINER }}
+      volumes:
+        - /var/run/docker.sock:/var/run/docker.sock
+
     steps:
       - name: Checkout
         uses: actions/checkout@v2
 
       - name: Running task on Intel GPU
         run: |
-          rm ~/borealis-runner/llm-ray.tar.gz -f
-          tar zcf ~/borealis-runner/llm-ray.tar.gz -C ~/actions-runner/_work/llm-ray .
+          rm ~/borealis-runner/llm-on-ray.tar.gz -f
+          tar zcf ~/borealis-runner/llm-on-ray.tar.gz -C ~/actions-runner/_work/llm-on-ray .
           cd ~/borealis-runner/
           python3 finetune_on_pvc.py --base_model "${{ matrix.model }}"
-
       - name: Test Summary
-        run: echo "to be continued"
+        run: echo "to be continued"

.github/workflows/workflow_inference.yml

@@ -16,7 +16,6 @@ jobs:
     name: inference test
     strategy:
       matrix:
-        # for mistral-7b-v0.1, we use bigdl-cpu to verify
         model: [ gpt-j-6b, gpt2, bloom-560m, opt-125m, mpt-7b, mistral-7b-v0.1, mpt-7b-bigdl, neural-chat-7b-v3-1 ]
         isPR:
           - ${{inputs.ci_type == 'pr'}}
@@ -32,10 +31,22 @@ jobs:
             model: mpt-7b
 
     runs-on: self-hosted
+
+    defaults:
+      run:
+        shell: bash
+    container:
+      image: ${{ vars.ACTIONS_RUNNER_CONTAINER_IMAGE }}
+      env:
+        http_proxy: ${{ vars.HTTP_PROXY_CONTAINER }}
+        https_proxy: ${{ vars.HTTPS_PROXY_CONTAINER }}
+      volumes:
+        - /var/run/docker.sock:/var/run/docker.sock
+
     steps:
       - name: Checkout
         uses: actions/checkout@v2
-
+      
       - name: Set Name Prefix
         id: "prefix"
         run: |
@@ -54,14 +65,15 @@ jobs:
             DF_SUFFIX=".cpu_and_deepspeed"
           fi
           PREFIX=${{steps.prefix.outputs.prefix}}
-          docker build ./ --build-arg CACHEBUST=1 --build-arg http_proxy=${{ vars.HTTP_PROXY_IMAGE_BUILD }} --build-arg https_proxy=${{ vars.HTTPS_PROXY_IMAGE_BUILD }} -f dev/docker/Dockerfile${DF_SUFFIX} -t ${PREFIX}:latest && yes | docker container prune && yes | docker image prune
+          docker build ./ --build-arg CACHEBUST=1 --build-arg http_proxy=${{ vars.HTTP_PROXY_CONTAINER }} --build-arg https_proxy=${{ vars.HTTPS_PROXY_CONTAINER }} -f dev/docker/Dockerfile${DF_SUFFIX} -t ${PREFIX}:latest && yes | docker container prune && yes
+          docker image prune -f
 
       - name: Start Docker Container
         run: |
           PREFIX=${{steps.prefix.outputs.prefix}}
           cid=$(docker ps -q --filter "name=${PREFIX}")
           if [[ ! -z "$cid" ]]; then docker stop $cid && docker rm $cid; fi
-          docker run -tid -v /mnt/DP_disk1/huggingface/cache/:/root/.cache/huggingface/hub -v .:/root/llm-ray -e http_proxy=${{ vars.HTTP_PROXY_CONTAINER_RUN }} -e https_proxy=${{ vars.HTTPS_PROXY_CONTAINER_RUN }} --name="${PREFIX}" --hostname="${PREFIX}-container" ${PREFIX}:latest
+          docker run -tid -v ${{ vars.MODEL_CACHE_PATH }}:/root/.cache/huggingface/hub -v ${{ vars.CODE_CHECKOUT_PATH }}:/root/llm-on-ray -e http_proxy=${{ vars.HTTP_PROXY_CONTAINER }} -e https_proxy=${{ vars.HTTPS_PROXY_CONTAINER }} --name="${PREFIX}" --hostname="${PREFIX}-container" ${PREFIX}:latest
 
       - name: Start Ray Cluster
         run: |
@@ -94,9 +106,15 @@ jobs:
             echo ${{ matrix.model }} is not supported!
           else
             docker exec "${PREFIX}" bash -c "python .github/workflows/config/update_inference_config.py --config_file inference/models/\"${{ matrix.model }}\".yaml --output_file \"${{ matrix.model }}\".yaml.deepspeed --deepspeed"
+<<<<<<< HEAD
             docker exec "${PREFIX}" bash -c "python inference/serve.py --config_file \"${{ matrix.model }}\".yaml.deepspeed --serve_simple"
             docker exec "${PREFIX}" bash -c "python examples/inference/api_server_simple/query_single.py --num_iter 1 --model_endpoint http://127.0.0.1:8000/${{ matrix.model }}"
             docker exec "${PREFIX}" bash -c "python examples/inference/api_server_simple/query_single.py --num_iter 1 --model_endpoint http://127.0.0.1:8000/${{ matrix.model }} --streaming_response"
+=======
+            docker exec "${PREFIX}" bash -c "KEEP_SERVE_TERMINAL='false' python inference/run_model_serve.py --config_file \"${{ matrix.model }}\".yaml.deepspeed"
+            docker exec "${PREFIX}" bash -c "python inference/run_model_infer.py --num_iter 1 --model_endpoint http://127.0.0.1:8000/${{ matrix.model }}"
+            docker exec "${PREFIX}" bash -c "python inference/run_model_infer.py --num_iter 1 --model_endpoint http://127.0.0.1:8000/${{ matrix.model }} --streaming_response"
+>>>>>>> opensource/main
           fi
 
       - name: Run Inference Test with DeepSpeed and Deltatuner
@@ -137,4 +155,7 @@ jobs:
           if [[ ! -z "$cid" ]]; then docker stop $cid && docker rm $cid; fi
 
       - name: Test Summary
-        run: echo "to be continued"
+        run: echo "to be continued"
+
+
+

.github/workflows/workflow_orders_nightly.yml

@@ -1,8 +1,8 @@
-name: llm-ray inference & finetune
+name: llm-ray inference & finetune nightly
 
 on:
   schedule:
-    - cron: "0 19 * * *"
+    - cron: "0 16 * * *"
 
 jobs:
 

.github/workflows/workflow_orders_on_merge.yml

@@ -0,0 +1,24 @@
+name: llm-ray inference & finetune
+
+on:
+  push:
+    branches:
+      - main
+    paths:
+      - '.github/**'
+      - 'docker/**'
+      - 'common/**'
+      - 'dev/docker/**'
+      - 'finetune/**'
+      - 'inference/**'
+      - 'rlhf/**'
+      - 'tools/**'
+      - 'pyproject.toml'
+
+jobs:
+
+  call-inference:
+    uses: ./.github/workflows/workflow_inference.yml
+
+  call-finetune:
+    uses: ./.github/workflows/workflow_finetune.yml

.github/workflows/workflow_orders.yml → .github/workflows/workflow_orders_on_pr.yml

@@ -13,6 +13,7 @@ on:
       - 'inference/**'
       - 'rlhf/**'
       - 'tools/**'
+      - 'pyproject.toml'
 
 jobs:
 

CODE_OF_CONDUCT.md

@@ -0,0 +1,131 @@
+# Contributor Covenant Code of Conduct
+
+## Our Pledge
+
+We as members, contributors, and leaders pledge to make participation in our
+community a harassment-free experience for everyone, regardless of age, body
+size, visible or invisible disability, ethnicity, sex characteristics, gender
+identity and expression, level of experience, education, socio-economic status,
+nationality, personal appearance, race, caste, color, religion, or sexual
+identity and orientation.
+
+We pledge to act and interact in ways that contribute to an open, welcoming,
+diverse, inclusive, and healthy community.
+
+## Our Standards
+
+Examples of behavior that contributes to a positive environment for our
+community include:
+
+* Demonstrating empathy and kindness toward other people
+* Being respectful of differing opinions, viewpoints, and experiences
+* Giving and gracefully accepting constructive feedback
+* Accepting responsibility and apologizing to those affected by our mistakes,
+  and learning from the experience
+* Focusing on what is best not just for us as individuals, but for the overall
+  community
+
+Examples of unacceptable behavior include:
+
+* The use of sexualized language or imagery, and sexual attention or advances of
+  any kind
+* Trolling, insulting or derogatory comments, and personal or political attacks
+* Public or private harassment
+* Publishing others' private information, such as a physical or email address,
+  without their explicit permission
+* Other conduct which could reasonably be considered inappropriate in a
+  professional setting
+
+## Enforcement Responsibilities
+
+Community leaders are responsible for clarifying and enforcing our standards of
+acceptable behavior and will take appropriate and fair corrective action in
+response to any behavior that they deem inappropriate, threatening, offensive,
+or harmful.
+
+Community leaders have the right and responsibility to remove, edit, or reject
+comments, commits, code, wiki edits, issues, and other contributions that are
+not aligned to this Code of Conduct, and will communicate reasons for moderation
+decisions when appropriate.
+
+## Scope
+
+This Code of Conduct applies within all community spaces, and also applies when
+an individual is officially representing the community in public spaces.
+Examples of representing our community include using an official e-mail address,
+posting via an official social media account, or acting as an appointed
+representative at an online or offline event.
+
+## Enforcement
+
+Instances of abusive, harassing, or otherwise unacceptable behavior may be
+reported to the community leaders responsible for enforcement at
+CommunityCodeOfConduct AT intel DOT com.
+All complaints will be reviewed and investigated promptly and fairly.
+
+All community leaders are obligated to respect the privacy and security of the
+reporter of any incident.
+
+## Enforcement Guidelines
+
+Community leaders will follow these Community Impact Guidelines in determining
+the consequences for any action they deem in violation of this Code of Conduct:
+
+### 1. Correction
+
+**Community Impact**: Use of inappropriate language or other behavior deemed
+unprofessional or unwelcome in the community.
+
+**Consequence**: A private, written warning from community leaders, providing
+clarity around the nature of the violation and an explanation of why the
+behavior was inappropriate. A public apology may be requested.
+
+### 2. Warning
+
+**Community Impact**: A violation through a single incident or series of
+actions.
+
+**Consequence**: A warning with consequences for continued behavior. No
+interaction with the people involved, including unsolicited interaction with
+those enforcing the Code of Conduct, for a specified period of time. This
+includes avoiding interactions in community spaces as well as external channels
+like social media. Violating these terms may lead to a temporary or permanent
+ban.
+
+### 3. Temporary Ban
+
+**Community Impact**: A serious violation of community standards, including
+sustained inappropriate behavior.
+
+**Consequence**: A temporary ban from any sort of interaction or public
+communication with the community for a specified period of time. No public or
+private interaction with the people involved, including unsolicited interaction
+with those enforcing the Code of Conduct, is allowed during this period.
+Violating these terms may lead to a permanent ban.
+
+### 4. Permanent Ban
+
+**Community Impact**: Demonstrating a pattern of violation of community
+standards, including sustained inappropriate behavior, harassment of an
+individual, or aggression toward or disparagement of classes of individuals.
+
+**Consequence**: A permanent ban from any sort of public interaction within the
+community.
+
+## Attribution
+
+This Code of Conduct is adapted from the [Contributor Covenant][homepage],
+version 2.1, available at
+[https://www.contributor-covenant.org/version/2/1/code_of_conduct.html][v2.1].
+
+Community Impact Guidelines were inspired by
+[Mozilla's code of conduct enforcement ladder][Mozilla CoC].
+
+For answers to common questions about this code of conduct, see the FAQ at
+[https://www.contributor-covenant.org/faq][FAQ]. Translations are available at
+[https://www.contributor-covenant.org/translations][translations].
+
+[homepage]: https://www.contributor-covenant.org
+[v2.1]: https://www.contributor-covenant.org/version/2/1/code_of_conduct.html
+[Mozilla CoC]: https://github.com/mozilla/diversity
+[FAQ]: https://www.contributor-covenant.org/faq