↓ 2 callersFunction_run_grouped_gemm_ws(kernel, batch_sizes, K=128, N=128, block_M=64, dtype="float16")
testing/python/transform/test_tilelang_transform_producer_consumer_ws.py:330
↓ 2 callersFunction_run_mma_atom(M, N, K, in_dtype, out_dtype, accum_dtype)
testing/python/language/test_tilelang_language_atom_mma.py:122
↓ 2 callersFunction_scan_fragment(
src: BufferLikeType,
dst: BufferLikeType,
dim: int,
reverse: bool,
op_key: str,
)
tilelang/language/scan_op.py:15
↓ 2 callersFunction_tl_vs_sparse_flashattn(batch, heads, seq_len, dim, vertical_size, slash_size)
examples/minference/example_vertical_slash_sparse_attn.py:17
↓ 2 callersFunctionassert_matmul_correctness(M, N, K, block_M, block_N, block_K, in_dtype, out_dtype, accum_dtype)
testing/python/kernel/test_tilelang_kernel_int8_gemm_tcgen5.py:41
↓ 2 callersFunctionassert_similar(x, y, eps=1e-2, name="tensor", assert_=False, print_=True)
examples/flash_decoding/example_gqa_decode.py:391
↓ 2 callersFunctionassert_tl_gemm_correctness(M, N, K, block_N, in_dtype, out_dtype, accum_dtype)
examples/deepseek_deepgemm/example_deepgemm_fp8_2xAcc.py:141
↓ 2 callersFunctionassert_tl_matmul_correctness(
M,
N,
K,
in_dtype,
out_dtype,
accum_dtype=T.float32,
a_transposed=False,
b_t
testing/python/amd/test_tilelang_gemm_mfma_preshuffle.py:270
↓ 2 callersFunctionatomic_add_program(K, M, N, block_M, block_N, dtype=T.float32)
testing/python/language/test_tilelang_language_atomic.py:11