reorder AMD tensor core benchmark test (#13860)

* reorder AMD tensor core benchmark test

* disable that
This commit is contained in:
chenyu
2025-12-28 12:29:51 -05:00
committed by GitHub
parent 066d96c397
commit f5090192c8

View File

@@ -429,13 +429,15 @@ jobs:
# LD_PRELOAD="/opt/rocm/lib/libhsa-runtime64.so" HSA=1 BIG=2 TORCHCUDA=1 python3 test/speed/external_test_speed_v_torch.py | tee torch_speed.txt
- name: Test speed vs theoretical
run: AMD=1 IGNORE_BEAM_CACHE=1 CCACHE=0 BEAM_DEBUG=1 DEBUG=1 python -m pytest -rA test/external/speed_v_theoretical.py --durations=20
- name: Test tensor cores
run: |
AMD=1 AMD_LLVM=0 python3 test/opt/test_tensor_cores.py
AMD=1 AMD_LLVM=1 python3 test/opt/test_tensor_cores.py
AMD=1 SHOULD_USE_TC=1 BFLOAT16=1 DEBUG=2 python3 extra/gemm/simple_matmul.py
- name: Test tensor cores AMD_LLVM=0
run: AMD=1 AMD_LLVM=0 python3 test/opt/test_tensor_cores.py
# TODO: this is flaky
# - name: Test tensor cores AMD_LLVM=1
# run: AMD=1 AMD_LLVM=1 python3 test/opt/test_tensor_cores.py
- name: Run Tensor Core GEMM (AMD)
run: AMD=1 SHOULD_USE_TC=1 HALF=1 DEBUG=2 ATOL=2e-2 python3 extra/gemm/simple_matmul.py | tee matmul_amd.txt
run: |
AMD=1 SHOULD_USE_TC=1 BFLOAT16=1 DEBUG=2 python3 extra/gemm/simple_matmul.py
AMD=1 SHOULD_USE_TC=1 HALF=1 DEBUG=2 ATOL=2e-2 python3 extra/gemm/simple_matmul.py | tee matmul_amd.txt
- name: Test AMD=1
run: DEBUG=2 AMD=1 python -m pytest -rA test/test_tiny.py
#- name: Test HIP=1