[CI] Remove triton version for compatibility bug; update req torch >=2.2 (#6018)

* remove triton version

* remove torch 2.2

* remove torch 2.1

* debug

* remove 2.1 build tests

* require torch >=2.2

---------

Co-authored-by: Edenzzzz <wtan45@wisc.edu>

.compatibility

@@ -1,4 +1,3 @@
-2.1.0-12.1.0
 2.2.2-12.1.0
 2.3.0-12.1.0
 2.4.0-12.4.1

.github/workflows/build_on_pr.yml

@@ -89,7 +89,7 @@ jobs:
     if: needs.detect.outputs.anyLibraryFileChanged == 'true'
     runs-on: [self-hosted, gpu]
     container:
-      image: hpcaitech/pytorch-cuda:2.1.0-12.1.0
+      image: hpcaitech/pytorch-cuda:2.2.2-12.1.0
       options: --gpus all --rm -v /dev/shm -v /data/scratch:/data/scratch
     timeout-minutes: 90
     defaults:

.github/workflows/build_on_schedule.yml

@@ -12,7 +12,7 @@ jobs:
     if: github.repository == 'hpcaitech/ColossalAI'
     runs-on: [self-hosted, gpu]
     container:
-      image: hpcaitech/pytorch-cuda:2.1.0-12.1.0
+      image: hpcaitech/pytorch-cuda:2.2.2-12.1.0
       options: --gpus all --rm -v /dev/shm -v /data/scratch/:/data/scratch/
     timeout-minutes: 90
     steps:

.github/workflows/doc_test_on_pr.yml

@@ -56,7 +56,7 @@ jobs:
     needs: detect-changed-doc
     runs-on: [self-hosted, gpu]
     container:
-      image: hpcaitech/pytorch-cuda:2.1.0-12.1.0
+      image: hpcaitech/pytorch-cuda:2.2.2-12.1.0
       options: --gpus all --rm
     timeout-minutes: 30
     defaults:

.github/workflows/doc_test_on_schedule.yml

@@ -12,7 +12,7 @@ jobs:
     name: Test the changed Doc
     runs-on: [self-hosted, gpu]
     container:
-      image: hpcaitech/pytorch-cuda:2.1.0-12.1.0
+      image: hpcaitech/pytorch-cuda:2.2.2-12.1.0
       options: --gpus all --rm
     timeout-minutes: 60
     steps:

.github/workflows/example_check_on_dispatch.yml

@@ -45,7 +45,7 @@ jobs:
       fail-fast: false
       matrix: ${{fromJson(needs.manual_check_matrix_preparation.outputs.matrix)}}
     container:
-      image: hpcaitech/pytorch-cuda:2.1.0-12.1.0
+      image: hpcaitech/pytorch-cuda:2.2.2-12.1.0
       options: --gpus all --rm -v /data/scratch/examples-data:/data/ -v /dev/shm
     timeout-minutes: 15
     steps:

.github/workflows/example_check_on_pr.yml

@@ -90,7 +90,7 @@ jobs:
       fail-fast: false
       matrix: ${{fromJson(needs.detect-changed-example.outputs.matrix)}}
     container:
-      image: hpcaitech/pytorch-cuda:2.1.0-12.1.0
+      image: hpcaitech/pytorch-cuda:2.2.2-12.1.0
       options: --gpus all --rm -v /data/scratch/examples-data:/data/ -v /dev/shm
     timeout-minutes: 30
     concurrency:

.github/workflows/example_check_on_schedule.yml

@@ -34,7 +34,7 @@ jobs:
       fail-fast: false
       matrix: ${{fromJson(needs.matrix_preparation.outputs.matrix)}}
     container:
-      image: hpcaitech/pytorch-cuda:2.1.0-12.1.0
+      image: hpcaitech/pytorch-cuda:2.2.2-12.1.0
       options: --gpus all --rm -v /data/scratch/examples-data:/data/ -v /dev/shm
     timeout-minutes: 30
     steps:

.github/workflows/run_chatgpt_examples.yml

@@ -19,7 +19,7 @@ jobs:
       github.event.pull_request.base.repo.full_name == 'hpcaitech/ColossalAI'
     runs-on: [self-hosted, gpu]
     container:
-      image: hpcaitech/pytorch-cuda:2.1.0-12.1.0
+      image: hpcaitech/pytorch-cuda:2.2.2-12.1.0
       options: --gpus all --rm -v /data/scratch/examples-data:/data/scratch/examples-data --shm-size=10.24gb
     timeout-minutes: 60
     defaults:

.github/workflows/run_chatgpt_unit_tests.yml

@@ -19,7 +19,7 @@ jobs:
       github.event.pull_request.base.repo.full_name == 'hpcaitech/ColossalAI'
     runs-on: [self-hosted, gpu]
     container:
-      image: hpcaitech/pytorch-cuda:2.1.0-12.1.0
+      image: hpcaitech/pytorch-cuda:2.2.2-12.1.0
       options: --gpus all --rm -v /data/scratch/examples-data:/data/scratch/examples-data
     timeout-minutes: 30
     defaults:

.github/workflows/run_colossalqa_unit_tests.yml

@@ -19,7 +19,7 @@ jobs:
       github.event.pull_request.base.repo.full_name == 'hpcaitech/ColossalAI'
     runs-on: [self-hosted, gpu]
     container:
-      image: hpcaitech/pytorch-cuda:2.1.0-12.1.0
+      image: hpcaitech/pytorch-cuda:2.2.2-12.1.0
       volumes:
         - /data/scratch/test_data_colossalqa:/data/scratch/test_data_colossalqa
         - /data/scratch/llama-tiny:/data/scratch/llama-tiny

README.md

@@ -420,7 +420,7 @@ Please visit our [documentation](https://www.colossalai.org/) and [examples](htt
 ## Installation
 
 Requirements:
-- PyTorch >= 2.1
+- PyTorch >= 2.2
 - Python >= 3.7
 - CUDA >= 11.0
 - [NVIDIA GPU Compute Capability](https://developer.nvidia.com/cuda-gpus) >= 7.0 (V100/RTX20 and higher)

requirements/requirements.txt

@@ -8,7 +8,7 @@ click
 fabric
 contexttimer
 ninja
-torch>=2.1.0,<=2.4.0
+torch>=2.2.0,<=2.4.0
 safetensors
 einops
 pydantic