aparler/c-llm
1
0
Fork 0
mirror of https://github.com/karpathy/llm.c.git synced 2026-07-28 20:35:09 -04:00
Code Issues Projects Releases Packages Wiki Activity Actions

Fix guarding logic, refactor

Browse source
This commit is contained in:
Aleksa Gordic 2024-06-17 14:12:05 +02:00
parent fa7f2b6763
commit a0a8795be1
6 changed files with 21 additions and 20 deletions
Download patch file Download diff file Expand all files Collapse all files

22
.github/workflows/ci_gpu.yml vendored
View file

@ -31,19 +31,19 @@ jobs:
run: python train_gpt2.py
- name: Compile training and testing program
run: make test_gpt2cu train_gpt2cu test_gpt2fp32cu train_gpt2fp32cu
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: |
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
@ -52,7 +52,7 @@ jobs:
- name: Run recompute LN
run: ./test_gpt2cu -r 2
- name: Build BF16 precision
run: PRECISION=BF16 make train_gpt2cu test_gpt2cu profile_gpt2cu
@ -67,18 +67,18 @@ jobs:
- 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
run: NO_OMP=1 make test_gpt2cu train_gpt2cu test_gpt2fp32cu train_gpt2fp32cu
- name: Train model (No OpenMP)
run: NO_OMP=1 ./train_gpt2cu
@ -88,14 +88,14 @@ jobs:
- 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:
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