Merge branch 'main' of github.com:flybird11111/ColossalAI into main

.cuda_ext.json

@@ -1,16 +1,16 @@
 {
   "build": [
     {
-      "torch_command": "pip install torch==1.12.1+cu102 torchvision==0.13.1+cu102 torchaudio==0.12.1 --extra-index-url https://download.pytorch.org/whl/cu102",
-      "cuda_image": "hpcaitech/cuda-conda:10.2"
+      "torch_command": "pip install torch==2.1.0 torchvision==0.16.0 torchaudio==2.1.0 --index-url https://download.pytorch.org/whl/cu121",
+      "cuda_image": "hpcaitech/cuda-conda:12.1"
     },
     {
-      "torch_command": "pip install torch==1.12.1+cu113 torchvision==0.13.1+cu113 torchaudio==0.12.1 --extra-index-url https://download.pytorch.org/whl/cu113",
-      "cuda_image": "hpcaitech/cuda-conda:11.3"
+      "torch_command": "pip install torch==2.1.0 torchvision==0.16.0 torchaudio==2.1.0 --index-url https://download.pytorch.org/whl/cu118",
+      "cuda_image": "hpcaitech/cuda-conda:11.8"
     },
     {
-      "torch_command": "pip install torch==1.12.1+cu116 torchvision==0.13.1+cu116 torchaudio==0.12.1 --extra-index-url https://download.pytorch.org/whl/cu116",
-      "cuda_image": "hpcaitech/cuda-conda:11.6"
+      "torch_command": "pip install torch==2.0.0 torchvision==0.15.1 torchaudio==2.0.1",
+      "cuda_image": "hpcaitech/cuda-conda:11.7"
     }
   ]
 }

.github/workflows/build_on_pr.yml

@@ -201,4 +201,4 @@ jobs:
         uses: actions/upload-artifact@v3
         with:
           name: report
-          path: report/
+          path: report/

.github/workflows/build_on_schedule.yml

@@ -83,4 +83,4 @@ jobs:
           SERVER_URL: ${{github.server_url }}
           REPO: ${{ github.repository }}
           RUN_ID: ${{ github.run_id }}
-          WEBHOOK_URL: ${{ secrets.LARK_NOTIFICATION_WEBHOOK_URL }}
+          WEBHOOK_URL: ${{ secrets.LARK_NOTIFICATION_WEBHOOK_URL }}

.github/workflows/compatiblity_test_on_dispatch.yml

@@ -83,7 +83,7 @@ jobs:
           fi
       - name: Install Colossal-AI
         run: |
-          CUDA_EXT=1 pip install -v .
+          BUILD_EXT=1 pip install -v .
           pip install -r requirements/requirements-test.txt
       - name: Unit Testing
         run: |

.github/workflows/compatiblity_test_on_pr.yml

@@ -78,7 +78,7 @@ jobs:
 
       - name: Install Colossal-AI
         run: |
-          CUDA_EXT=1 pip install -v .
+          BUILD_EXT=1 pip install -v .
           pip install -r requirements/requirements-test.txt
       - name: Unit Testing
         run: |

.github/workflows/compatiblity_test_on_schedule.yml

@@ -75,7 +75,7 @@ jobs:
 
       - name: Install Colossal-AI
         run: |
-          CUDA_EXT=1 pip install -v .
+          BUILD_EXT=1 pip install -v .
           pip install -r requirements/requirements-test.txt
 
       - name: Unit Testing

.github/workflows/cuda_ext_check_before_merge.yml

@@ -51,4 +51,4 @@ jobs:
 
       - name: Build
         run: |
-          CUDA_EXT=1 pip install -v .
+          BUILD_EXT=1 pip install -v .

.github/workflows/doc_test_on_pr.yml

@@ -89,7 +89,7 @@ jobs:
       - name: Install ColossalAI
         run: |
           source activate pytorch
-          CUDA_EXT=1 pip install -v .
+          BUILD_EXT=1 pip install -v .
 
       - name: Test the Doc
         run: |

.github/workflows/doc_test_on_schedule.yml

@@ -32,7 +32,7 @@ jobs:
 
       - name: Install ColossalAI
         run: |
-          CUDA_EXT=1 pip install -v .
+          BUILD_EXT=1 pip install -v .
 
       - name: Install Doc Test Requirements
         run: |

.github/workflows/example_check_on_dispatch.yml

@@ -53,7 +53,7 @@ jobs:
         uses: actions/checkout@v3
       - name: Install Colossal-AI
         run: |
-          CUDA_EXT=1 pip install -v .
+          BUILD_EXT=1 pip install -v .
       - name: Test the example
         run: |
           dir=${{ matrix.directory }}

.github/workflows/example_check_on_pr.yml

@@ -88,7 +88,7 @@ jobs:
 
       - name: Install Colossal-AI
         run: |
-          CUDA_EXT=1 pip install -v .
+          BUILD_EXT=1 pip install -v .
 
       - name: Test the example
         run: |

.github/workflows/example_check_on_schedule.yml

@@ -42,7 +42,7 @@ jobs:
 
       - name: Install Colossal-AI
         run: |
-          CUDA_EXT=1 pip install -v .
+          BUILD_EXT=1 pip install -v .
 
       - name: Traverse all files
         run: |

.github/workflows/release_nightly_on_schedule.yml

@@ -6,19 +6,23 @@ on:
     - cron:  '0 0 * * 6' # release on every Sunday 00:00 UTC time
 
 jobs:
-  build-n-publish:
+  publish:
     if: github.repository == 'hpcaitech/ColossalAI'
     name: Build and publish Python 🐍 distributions 📦 to PyPI
     runs-on: ubuntu-latest
     timeout-minutes: 20
+    outputs:
+      status: ${{ steps.publish.outcome }}
     steps:
     - uses: actions/checkout@v2
 
     - uses: actions/setup-python@v2
       with:
         python-version: '3.8.14'
 
-    - run: NIGHTLY=1 python setup.py sdist build
+    - run: |
+        python .github/workflows/scripts/update_setup_for_nightly.py
+        python setup.py sdist build
 
     # publish to PyPI if executed on the main branch
     - name: Publish package to PyPI
@@ -31,7 +35,7 @@ jobs:
 
   notify:
     name: Notify Lark via webhook
-    needs: build-n-publish
+    needs: publish
     runs-on: ubuntu-latest
     if: ${{ always() }} && github.repository == 'hpcaitech/ColossalAI'
     steps:
@@ -62,4 +66,4 @@ jobs:
           REPO: ${{ github.repository }}
           RUN_ID: ${{ github.run_id }}
           WEBHOOK_URL: ${{ secrets.LARK_NOTIFICATION_WEBHOOK_URL }}
-          STATUS: ${{ steps.publish.outcome }}
+          STATUS: ${{ needs.publish.outputs.status }}

.github/workflows/release_test_pypi_before_merge.yml

@@ -49,6 +49,6 @@ jobs:
         # we need to install the requirements.txt first
         # as test-pypi may not contain the distributions for libs listed in the txt file
         pip install -r requirements/requirements.txt
-        pip install --index-url https://test.pypi.org/simple/ colossalai==$VERSION
+        pip install --index-url https://test.pypi.org/simple/ --extra-index-url https://pypi.python.org/pypi colossalai==$VERSION
       env:
         VERSION: ${{ steps.prep-version.outputs.version }}

.github/workflows/scripts/update_setup_for_nightly.py

@@ -0,0 +1,34 @@
+from datetime import datetime
+
+
+def open_setup_file():
+    with open("setup.py", "r") as f:
+        file_lines = f.readlines()
+    return file_lines
+
+
+def replace_nightly_package_info(file_lines):
+    version = datetime.today().strftime("%Y.%m.%d")
+    package_name = "colossalai-nightly"
+
+    for idx, line in enumerate(file_lines):
+        if "version = get_version()" in line:
+            file_lines[idx] = f'version = "{version}"\n'
+        if 'package_name = "colossalai"' in line:
+            file_lines[idx] = f'package_name = "{package_name}"\n'
+    return file_lines
+
+
+def write_setup_file(file_lines):
+    with open("setup.py", "w") as f:
+        f.writelines(file_lines)
+
+
+def main():
+    file_lines = open_setup_file()
+    file_lines = replace_nightly_package_info(file_lines)
+    write_setup_file(file_lines)
+
+
+if __name__ == "__main__":
+    main()

README.md

@@ -9,7 +9,7 @@
    <a href="https://www.colossalai.org/"> Documentation </a> |
    <a href="https://github.com/hpcaitech/ColossalAI/tree/main/examples"> Examples </a> |
    <a href="https://github.com/hpcaitech/ColossalAI/discussions"> Forum </a> |
-   <a href="https://medium.com/@hpcaitech"> Blog </a></h3>
+   <a href="https://hpc-ai.com/blog"> Blog </a></h3>
 
    [![GitHub Repo stars](https://img.shields.io/github/stars/hpcaitech/ColossalAI?style=social)](https://github.com/hpcaitech/ColossalAI/stargazers)
    [![Build](https://github.com/hpcaitech/ColossalAI/actions/workflows/build_on_schedule.yml/badge.svg)](https://github.com/hpcaitech/ColossalAI/actions/workflows/build_on_schedule.yml)
@@ -25,16 +25,13 @@
 </div>
 
 ## Latest News
+* [2024/03] [Open-Sora：Sora Replication Solution with 46% Cost Reduction, Sequence Expansion to Nearly a Million](https://hpc-ai.com/blog/open-sora)
 * [2024/01] [Inference Performance Improved by 46%, Open Source Solution Breaks the Length Limit of LLM for Multi-Round Conversations](https://hpc-ai.com/blog/Colossal-AI-SwiftInfer)
 * [2024/01] [Construct Refined 13B Private Model With Just $5000 USD, Upgraded Colossal-AI Llama-2 Open Source](https://hpc-ai.com/blog/colossal-llama-2-13b)
 * [2023/11] [Enhanced MoE Parallelism, Open-source MoE Model Training Can Be 9 Times More Efficient](https://www.hpc-ai.tech/blog/enhanced-moe-parallelism-open-source-moe-model-training-can-be-9-times-more-efficient)
 * [2023/09] [One Half-Day of Training Using a Few Hundred Dollars Yields Similar Results to Mainstream Large Models, Open-Source and Commercial-Free Domain-Specific LLM Solution](https://www.hpc-ai.tech/blog/one-half-day-of-training-using-a-few-hundred-dollars-yields-similar-results-to-mainstream-large-models-open-source-and-commercial-free-domain-specific-llm-solution)
 * [2023/09] [70 Billion Parameter LLaMA2 Model Training Accelerated by 195%](https://www.hpc-ai.tech/blog/70b-llama2-training)
 * [2023/07] [HPC-AI Tech Raises 22 Million USD in Series A Funding](https://www.hpc-ai.tech/blog/hpc-ai-tech-raises-22-million-usd-in-series-a-funding-to-fuel-team-expansion-and-business-growth)
-* [2023/07] [65B Model Pretraining Accelerated by 38%, Best Practices for Building LLaMA-Like Base Models Open-Source](https://www.hpc-ai.tech/blog/large-model-pretraining)
-* [2023/03] [ColossalChat: An Open-Source Solution for Cloning ChatGPT With a Complete RLHF Pipeline](https://medium.com/@yangyou_berkeley/colossalchat-an-open-source-solution-for-cloning-chatgpt-with-a-complete-rlhf-pipeline-5edf08fb538b)
-* [2023/03] [Intel and Colossal-AI Partner to Deliver Cost-Efficient Open-Source Solution for Protein Folding Structure Prediction](https://www.hpc-ai.tech/blog/intel-habana)
-* [2023/03] [AWS and Google Fund Colossal-AI with Startup Cloud Programs](https://www.hpc-ai.tech/blog/aws-and-google-fund-colossal-ai-with-startup-cloud-programs)
 
 ## Table of Contents
 <ul>
@@ -43,6 +40,7 @@
  <li>
    <a href="#Colossal-AI-in-the-Real-World">Colossal-AI for Real World Applications</a>
    <ul>
+     <li><a href="#Open-Sora">Open-Sora: Open-Sora：Sora Replication Solution with 46% Cost Reduction, Sequence Expansion to Nearly a Million</a></li>
      <li><a href="#Colossal-LLaMA-2">Colossal-LLaMA-2: One Half-Day of Training Using a Few Hundred Dollars Yields Similar Results to Mainstream Large Models, Open-Source and Commercial-Free Domain-Specific Llm Solution</a></li>
      <li><a href="#ColossalChat">ColossalChat: An Open-Source Solution for Cloning ChatGPT With a Complete RLHF Pipeline</a></li>
      <li><a href="#AIGC">AIGC: Acceleration of Stable Diffusion</a></li>
@@ -126,6 +124,20 @@ distributed training and inference in a few lines.
 <p align="right">(<a href="#top">back to top</a>)</p>
 
 ## Colossal-AI in the Real World
+### Open-Sora
+
+[Open-Sora](https://github.com/hpcaitech/Open-Sora)：Sora Replication Solution with 46% Cost Reduction, Sequence Expansion to Nearly a Million
+[[code]](https://github.com/hpcaitech/Open-Sora)
+[[blog]](https://hpc-ai.com/blog/open-sora)
+
+<p id="diffusion_demo" align="center">
+<img src="https://raw.githubusercontent.com/hpcaitech/public_assets/main/applications/sora/open-sora-1.png" width=600/>
+</p>
+
+<p id="diffusion_demo" align="center">
+<img src="https://raw.githubusercontent.com/hpcaitech/public_assets/main/applications/sora/open-sora-2.png" width=600/>
+</p>
+
 
 ### Colossal-LLaMA-2