diff --git a/.github/workflows/benchmark.yml b/.github/workflows/benchmark.yml index c9e9100b59..08d633e92b 100644 --- a/.github/workflows/benchmark.yml +++ b/.github/workflows/benchmark.yml @@ -153,12 +153,14 @@ jobs: run: HSA=1 HALF=1 DEBUG=2 python3 extra/gemm/simple_matmul.py | tee matmul.txt - name: Run Stable Diffusion run: HSA=1 python3 examples/stable_diffusion.py --seed 0 --noshow --timing | tee sd.txt - - name: Run LLaMA + - name: Run LLaMA 7B run: | HSA=1 JIT=0 python3 examples/llama.py --gen 1 --prompt "Hello." --count 10 --temperature 0 --timing | tee llama_unjitted.txt HSA=1 JIT=1 python3 examples/llama.py --gen 1 --prompt "Hello." --count 10 --temperature 0 --timing | tee llama_jitted.txt - - name: Run LLaMA with BEAM + - name: Run LLaMA 7B with BEAM run: HSA=1 JIT=1 BEAM=2 CACHELEVEL=0 python3 examples/llama.py --gen 1 --prompt "Hello." --count 10 --temperature 0 --timing | tee llama_beam.txt + - name: Run LLaMA 7B on 6 GPUs + run: HSA=1 python3 examples/llama.py --gen 1 --size 7B --shard 6 --prompt "Hello." --count 10 --temperature 0 --timing | tee llama_six_gpu.txt - name: Run LLaMA-2 70B run: HSA=1 python3 examples/llama.py --gen 2 --size 70B --shard 6 --prompt "Hello." --count 10 --temperature 0 --timing | tee llama_2_70B.txt - name: Run Mixtral 8x7B @@ -176,6 +178,7 @@ jobs: llama_unjitted.txt llama_jitted.txt llama_beam.txt + llama_six_gpu.txt llama_2_70B.txt gpt2_unjitted.txt gpt2_jitted.txt