↓ 14 callersFunctionkernel(
A,
B,
block_M=None,
block_N=None,
block_K=None,
num_stages=None,
thread_num=None
examples/analyze/example_gemm_analyze.py:12
↓ 14 callersFunctionrun_gemm(
M,
N,
K,
trans_A,
trans_B,
in_dtype,
out_dtype,
dtypeAccum,
block_M,
testing/python/kernel/test_tilelang_kernel_gemm.py:52
↓ 10 callersFunctionrun_cumsum(M, N, block_M, block_N, dim=0, reverse=False, dtype=T.float32, scope="smem")
testing/python/language/test_tilelang_language_scan.py:52
↓ 9 callersFunctionrun_cummax(M, N, block_M, block_N, dim=0, reverse=False, dtype=T.float32, scope="smem")
testing/python/language/test_tilelang_language_scan.py:366