From d8dc43ad06c2eda0758bbbc8ced60d364ec99bda Mon Sep 17 00:00:00 2001 From: chenyu Date: Thu, 27 Jun 2024 15:20:34 -0400 Subject: [PATCH] remove JIT_BATCH_SIZE=4 from gpt2 NV benchmark (#5198) this no longer helps --- .github/workflows/benchmark.yml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/.github/workflows/benchmark.yml b/.github/workflows/benchmark.yml index 79ae8590af..484b5e3b6b 100644 --- a/.github/workflows/benchmark.yml +++ b/.github/workflows/benchmark.yml @@ -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)