github/ColossalAI
1
0
Fork 0
mirror of https://github.com/hpcaitech/ColossalAI.git synced 2025-09-01 09:07:51 +00:00
Code Issues Packages Projects Releases Wiki Activity

[lazy] support from_pretrained (#4801)

Browse Source 
* [lazy] patch from pretrained

* [lazy] fix from pretrained and add tests

* [devops] update ci
This commit is contained in:
Hongxin Liu
2023-09-26 11:04:11 +08:00
committed by GitHub
parent 64a08b2dc3
commit 4965c0dabd
11 changed files with 397 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
.github/workflows/build_on_pr.yml vendored
View File

@@ -141,7 +141,7 @@ jobs:
runs-on: [self-hosted, gpu]
container:
image: hpcaitech/pytorch-cuda:1.12.0-11.3.0
options: --gpus all --rm -v /data/scratch/cifar-10:/data/scratch/cifar-10
options: --gpus all --rm -v /data/scratch/cifar-10:/data/scratch/cifar-10 -v /data/scratch/llama-tiny:/data/scratch/llama-tiny
timeout-minutes: 60
defaults:
run:
@@ -214,6 +214,7 @@ jobs:
NCCL_SHM_DISABLE: 1
LD_LIBRARY_PATH: /github/home/.tensornvme/lib:/usr/local/nvidia/lib:/usr/local/nvidia/lib64
TESTMON_CORE_PKGS: /__w/ColossalAI/ColossalAI/requirements/requirements.txt,/__w/ColossalAI/ColossalAI/requirements/requirements-test.txt
LLAMA_PATH: /data/scratch/llama-tiny
- name: Store Testmon Cache
run: |

3
.github/workflows/build_on_schedule.yml vendored
View File

@@ -13,7 +13,7 @@ jobs:
runs-on: [self-hosted, 8-gpu]
container:
image: hpcaitech/pytorch-cuda:1.12.0-11.3.0
options: --gpus all --rm -v /data/scratch/cifar-10:/data/scratch/cifar-10
options: --gpus all --rm -v /data/scratch/cifar-10:/data/scratch/cifar-10 -v /data/scratch/llama-tiny:/data/scratch/llama-tiny
timeout-minutes: 40
steps:
- name: Check GPU Availability # ensure all GPUs have enough memory
@@ -64,6 +64,7 @@ jobs:
env:
DATA: /data/scratch/cifar-10
LD_LIBRARY_PATH: /github/home/.tensornvme/lib:/usr/local/nvidia/lib:/usr/local/nvidia/lib64
LLAMA_PATH: /data/scratch/llama-tiny
- name: Notify Lark
id: message-preparation

3
.github/workflows/compatiblity_test_on_dispatch.yml vendored
View File

@@ -50,7 +50,7 @@ jobs:
matrix: ${{fromJson(needs.matrix_preparation.outputs.matrix)}}
container:
image: ${{ matrix.container }}
options: --gpus all --rm -v /data/scratch/cifar-10:/data/scratch/cifar-10
options: --gpus all --rm -v /data/scratch/cifar-10:/data/scratch/cifar-10 -v /data/scratch/llama-tiny:/data/scratch/llama-tiny
timeout-minutes: 120
steps:
- name: Install dependencies
@@ -92,3 +92,4 @@ jobs:
DATA: /data/scratch/cifar-10
NCCL_SHM_DISABLE: 1
LD_LIBRARY_PATH: /github/home/.tensornvme/lib:/usr/local/nvidia/lib:/usr/local/nvidia/lib64
LLAMA_PATH: /data/scratch/llama-tiny

3
.github/workflows/compatiblity_test_on_pr.yml vendored
View File

@@ -41,7 +41,7 @@ jobs:
matrix: ${{fromJson(needs.matrix_preparation.outputs.matrix)}}
container:
image: ${{ matrix.container }}
options: --gpus all --rm -v /data/scratch/cifar-10:/data/scratch/cifar-10
options: --gpus all --rm -v /data/scratch/cifar-10:/data/scratch/cifar-10 -v /data/scratch/llama-tiny:/data/scratch/llama-tiny
timeout-minutes: 120
concurrency:
group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}-run-test-${{ matrix.container }}
@@ -87,3 +87,4 @@ jobs:
DATA: /data/scratch/cifar-10
NCCL_SHM_DISABLE: 1
LD_LIBRARY_PATH: /github/home/.tensornvme/lib:/usr/local/nvidia/lib:/usr/local/nvidia/lib64
LLAMA_PATH: /data/scratch/llama-tiny

3
.github/workflows/compatiblity_test_on_schedule.yml vendored
View File

@@ -38,7 +38,7 @@ jobs:
matrix: ${{fromJson(needs.matrix_preparation.outputs.matrix)}}
container:
image: ${{ matrix.container }}
options: --gpus all --rm -v /data/scratch/cifar-10:/data/scratch/cifar-10
options: --gpus all --rm -v /data/scratch/cifar-10:/data/scratch/cifar-10 -v /data/scratch/llama-tiny:/data/scratch/llama-tiny
timeout-minutes: 120
steps:
- name: Install dependencies
@@ -85,6 +85,7 @@ jobs:
DATA: /data/scratch/cifar-10
NCCL_SHM_DISABLE: 1
LD_LIBRARY_PATH: /github/home/.tensornvme/lib:/usr/local/nvidia/lib:/usr/local/nvidia/lib64
LLAMA_PATH: /data/scratch/llama-tiny
- name: Notify Lark
id: message-preparation