remove JIT_BATCH_SIZE=4 from gpt2 NV benchmark (#5198)

this no longer helps
This commit is contained in:
chenyu
2024-06-27 15:20:34 -04:00
committed by GitHub
parent 345bcc2099
commit d8dc43ad06

View File

@@ -183,7 +183,7 @@ jobs:
- name: Run GPT2 w HALF
run: NV=1 JIT=1 HALF=1 python3 examples/gpt2.py --count 10 --temperature 0 --timing | tee gpt2_half.txt
- name: Run GPT2 w HALF/BEAM
run: NV=1 JIT=1 HALF=1 JITBEAM=2 IGNORE_BEAM_CACHE=1 CAST_BEFORE_VIEW=0 JIT_BATCH_SIZE=4 python3 examples/gpt2.py --count 10 --temperature 0 --timing | tee gpt2_half_beam.txt
run: NV=1 JIT=1 HALF=1 JITBEAM=2 IGNORE_BEAM_CACHE=1 CAST_BEFORE_VIEW=0 python3 examples/gpt2.py --count 10 --temperature 0 --timing | tee gpt2_half_beam.txt
- uses: actions/upload-artifact@v4
with:
name: Speed (NVIDIA)