From f30fb192b71b4f2c29a67088573c63d15e0445e6 Mon Sep 17 00:00:00 2001 From: chenyu Date: Wed, 13 Mar 2024 13:26:30 -0400 Subject: [PATCH] resnet eval on tinybox ci (#3714) --- .github/workflows/benchmark.yml | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/.github/workflows/benchmark.yml b/.github/workflows/benchmark.yml index 7b09569809..1a3d413c8f 100644 --- a/.github/workflows/benchmark.yml +++ b/.github/workflows/benchmark.yml @@ -141,6 +141,8 @@ jobs: ln -s ~/tinygrad/extra/datasets/cifar-10-python.tar.gz extra/datasets/cifar-10-python.tar.gz ln -s /raid/weights/mixtral-8x7b-32kseqlen weights/mixtral-8x7b-32kseqlen ln -s /raid/weights/LLaMA-2 weights/LLaMA-2 + mkdir -p extra/datasets + ln -s /raid/datasets/imagenet extra/datasets/imagenet - name: Run model inference benchmark run: LD_PRELOAD="/opt/rocm/lib/libhsa-runtime64.so" HSA=1 NOCLANG=1 python3 test/external/external_model_benchmark.py - name: Test speed vs torch @@ -173,6 +175,8 @@ jobs: run: time HSA=1 HALF=1 LATEWINO=1 STEPS=1000 TARGET_EVAL_ACC_PCT=93 python3 examples/hlb_cifar10.py | tee train_cifar_one_gpu.txt - name: Run full CIFAR training steps w 6 GPUS run: time HSA=1 HALF=1 STEPS=350 BS=1536 GPUS=6 TARGET_EVAL_ACC_PCT=93 python3 examples/hlb_cifar10.py | tee train_cifar_six_gpu.txt + - name: Run MLPerf resnet eval on training data + run: time HSA=1 MODEL=resnet python3 examples/mlperf/model_eval.py - uses: actions/upload-artifact@v4 with: name: Speed (AMD)