Skip to content

[refactor] Make llm.c modular #7

[refactor] Make llm.c modular

[refactor] Make llm.c modular #7

Workflow file for this run

name: GPU Builds and Tests
on:
create:
workflow_dispatch:
push:
branches:
- master
pull_request:
branches:
- master
jobs:
build-and-test-gpu:
runs-on: ubicloud-gpu-standard-1-latest
steps:
- name: Checkout code
uses: actions/checkout@v4
- name: Install OpenMP
run: sudo apt-get update && sudo apt-get install -y libomp-dev
- name: Install dependencies
run: pip install -r requirements.txt
- name: Run preprocessing
run: python dev/data/tinyshakespeare.py
- name: Train model
run: python train_gpt2.py
- name: Compile training and testing program
run: make test_gpt2cu train_gpt2cu test_gpt2fp32cu train_gpt2fp32cu
- name: Train model (With OpenMP)
run: OMP_NUM_THREADS=8 ./train_gpt2cu
- name: Train model (FP32) with gpt2_124M.bin
run: |
PRECISION=FP32 make train_gpt2cu
./train_gpt2cu -b 4 -t 64 -l 1e-4 -v 200 -s 200 -a 1 -x 10 -e gpt2_124M.bin
- name: Build FP32 precision
run: PRECISION=FP32 make test_gpt2cu profile_gpt2cu
- name: Run default
run: ./test_gpt2cu
- name: Run no recompute GeLU
run: ./test_gpt2cu -r 0
- name: Run recompute LN
run: ./test_gpt2cu -r 2
- name: Build BF16 precision
run: PRECISION=BF16 make train_gpt2cu test_gpt2cu profile_gpt2cu
- name: Run default
run: ./test_gpt2cu
- name: Run no recompute GeLU
run: ./test_gpt2cu -r 0
- name: Run no master weights
run: ./test_gpt2cu -w 0
- name: Run recompute LN
run: ./test_gpt2cu -r 2
- name: Train model fp32 (With OpenMP)
run: OMP_NUM_THREADS=8 ./train_gpt2fp32cu
- name: Execute testing program (With OpenMP)
run: OMP_NUM_THREADS=8 ./test_gpt2cu
- name: Execute testing program fp32 (With OpenMP)
run: OMP_NUM_THREADS=8 ./test_gpt2fp32cu
- name: Compile training and testing program without OpenMP
run: NO_OMP=1 make test_gpt2cu train_gpt2cu test_gpt2fp32cu train_gpt2fp32cu
- name: Train model (No OpenMP)
run: NO_OMP=1 ./train_gpt2cu
- name: Train model fp32 (No OpenMP)
run: NO_OMP=1 ./train_gpt2fp32cu
- name: Execute testing program (No OpenMP)
run: ./test_gpt2cu -b 32
- name: Execute testing program fp32 (No OpenMP)
run: ./test_gpt2fp32cu
- name: Install cuDNN-frontend
run:
git clone https://github.com/NVIDIA/cudnn-frontend.git
- name: Build with cuDNN
run: USE_CUDNN=1 make test_gpt2cu train_gpt2cu test_gpt2fp32cu train_gpt2fp32cu
- name: Train model with cuDNN
run: ./train_gpt2cu
- name: Train model fp32 with cuDNN
run: ./train_gpt2fp32cu
- name: Execute testing program with cuDNN
run: ./test_gpt2cu
- name: Execute testing program fp32 with cuDNN
run: ./test_gpt2fp32cu
unit-tests-gpu:
runs-on: ubicloud-gpu-standard-1-latest
steps:
- name: Checkout code
uses: actions/checkout@v4
- name: Test Device<->File IO
run: cd dev/test && nvcc -o device_file_io device_file_io.cu && ./device_file_io