↓ 1 callersFunction_compress_fn(D, dtype, meta_dtype, block_M=_BLOCK_M, block_K=_BLOCK_K, elem_per_thread=_ELEM_PER_THREAD)
tilelang/utils/sparse.py:44
↓ 1 callersFunction_do_mma(c_val, da_val, db_val, dv_val, sc_val, m0_val, m1_val, m2_val, m3_val, *, loc=None, ip=None)
tilelang/contrib/cutedsl/gemm_tcgen05.py:167
↓ 1 callersFunction_do_mma_ts(c_val, a_val, db_val, dv_val, sc_val, m0_val, m1_val, m2_val, m3_val, *, loc=None, ip=None)
tilelang/contrib/cutedsl/gemm_tcgen05.py:283
↓ 1 callersFunction_do_mma_ws(c_val, da_val, db_val, dv_val, sc_val, *, loc=None, ip=None)
tilelang/contrib/cutedsl/gemm_tcgen05.py:227
↓ 1 callersFunction_fadd_f32(a: Float32, b: Float32, *, rounding: str = "rn", loc=None, ip=None)
tilelang/contrib/cutedsl/ieee_math.py:31
↓ 1 callersFunction_fdiv_f32(a: Float32, b: Float32, *, rounding: str = "rn", loc=None, ip=None)
tilelang/contrib/cutedsl/ieee_math.py:133
↓ 1 callersFunction_fmaf_f32(a: Float32, b: Float32, c: Float32, *, rounding: str = "rn", loc=None, ip=None)
tilelang/contrib/cutedsl/ieee_math.py:82
↓ 1 callersFunction_fmul_f32(a: Float32, b: Float32, *, rounding: str = "rn", loc=None, ip=None)
tilelang/contrib/cutedsl/ieee_math.py:65
↓ 1 callersFunction_forward(ctx, q, k, v, block_sparse_mask, sm_scale, BLOCK_M=64, BLOCK_N=64, num_warps=None, num_stages=1, out=None)
benchmark/blocksparse_attention/benchmark_triton_block_sparse_fmha.py:194
↓ 1 callersFunction_forward(ctx, q, k, v, block_sparse_mask, sm_scale, BLOCK_M=64, BLOCK_N=64, num_warps=None, num_stages=1, out=None)
examples/blocksparse_attention/block_sparse_attn_triton.py:194
↓ 1 callersFunction_forward(ctx, q, k, v, block_sparse_mask, sm_scale, BLOCK_M=64, BLOCK_N=64, num_warps=None, num_stages=1, out=None)
examples/seer_attention/block_sparse_attn_triton.py:189