run HALF GPT2 in nvidia benchmark in addition to HALF/BEAM (#2811)

easier to separate the issue between HALF and BEAM when it failed
This commit is contained in:
chenyu
2023-12-17 02:24:55 -05:00
committed by GitHub
parent bad0ff60b7
commit 4e2a92cee1

View File

@@ -81,6 +81,8 @@ jobs:
run: |
CUDA=1 JIT=0 python3 examples/gpt2.py --prompt "Hello." --count 10 --temperature 0 --timing | tee gpt2_unjitted.txt
CUDA=1 JIT=1 python3 examples/gpt2.py --prompt "Hello." --count 10 --temperature 0 --timing | tee gpt2_jitted.txt
- name: Run GPT2 w HALF
run: CUDA=1 JIT=1 HALF=1 python3 examples/gpt2.py --count 10 --temperature 0 --timing
- name: Run GPT2 w HALF/BEAM
run: CUDA=1 JIT=1 HALF=1 BEAM=4 CACHELEVEL=0 python3 examples/gpt2.py --count 10 --temperature 0 --timing | tee gpt2_half_beam.txt
- uses: actions/upload-artifact@v3