↓ 3 callersFunction_make_gemm_kernel(M, N, K, block_M, block_N, block_K, in_dtype, out_dtype, accum_dtype)
testing/python/kernel/test_tilelang_kernel_gemm_sm75.py:8
↓ 3 callersMethod_parse_buffer_ndExtract (buffer, extra_indices, row_offset, col_offset, stride) from Buffer or BufferRegion. For 2D buffers, extra_indices is an empty tuple.
tilelang/metal/intrinsics/metal_macro_generator.py:70
↓ 3 callersFunction_resolve_cache_dispatch(
target: str | Target | None,
execution_backend: Literal["auto", "tvm_ffi", "cython", "nvrtc", "torch
tilelang/cache/__init__.py:42
↓ 3 callersFunctionassert_gemm(
M,
N,
K,
block_M,
block_N,
block_K,
dtype=T.float32,
accum_dtype=T.float32,
testing/python/metal/test_metal_codegen.py:36
↓ 3 callersFunctionassert_metal_codegen(
M,
N,
K,
block_M,
block_N,
block_K,
dtype=T.float32,
accum_dtype=T.float32,
testing/python/metal/test_metal_codegen_linux.py:40
↓ 3 callersFunctionassert_tl_matmul_correctness(M, N, K, in_dtype, out_dtype, accum_dtype)
examples/bitnet-1.58b/kernel_benchmark/tl_int8xint8.py:179
↓ 3 callersFunctionassert_tl_matmul_correctness(M, N, K, in_dtype, out_dtype, accum_dtype)
testing/python/kernel/test_tilelang_kernel_gemm_simt.py:132
↓ 3 callersFunctionchunk_bwd_dqkwg(
B,
S,
H,
DK,
DV,
scale,
chunk_size,
input_dtype,
gate_dtype,
block_D
examples/kda/chunk_bwd_dqkwg.py:68
↓ 3 callersFunctionchunk_gated_delta_rule_bwd_dhu(
q: torch.Tensor,
k: torch.Tensor,
w: torch.Tensor,
do: torch.Tensor,
dv: torch.Tensor,
examples/kda/FLA_KDA/fla_chunk_delta.py:524
↓ 3 callersFunctiondot(x1, x2, y1, y2, buf, out, tilesize, n_stream)
examples/deepseek_mhc/example_mhc_bwd.py:67
↓ 3 callersFunctionflashattn(batch, heads, groups, seqlen_kv, dim, block_N, block_H, num_split, num_stages, threads)
examples/flash_decoding/example_gqa_decode.py:50
↓ 3 callersFunctionflashattn(batch, heads, seq_len, dim, is_causal, block_M=64, block_N=64, num_stages=1, threads=128)
examples/flash_attention/example_mha_fwd_bshd.py:23
↓ 3 callersFunctionflashattn(batch, heads, seq_len, dim, is_causal, groups=1, block_M=64, block_N=64, num_stages=0, threads=128)
examples/flash_attention/example_gqa_fwd_bshd.py:68
↓ 3 callersFunctionflashattn(batch_size, UQ, UKV, heads, dim, is_causal, block_M=64, block_N=64, num_stages=1, threads=128)
examples/flash_attention/example_mha_fwd_varlen.py:27
↓ 3 callersFunctionflashattn(batch, heads, seq_q, seq_kv, dim, is_causal, block_M=64, block_N=64, num_stages=1, threads=128)
examples/flash_attention/example_mha_fwd_bhsd.py:23
↓ 3 callersFunctionflashattn(batch, heads, heads_kv, dim, dim_v, block_N, block_H, num_stages, threads)
examples/blocksparse_attention/example_tilelang_sparse_gqa_decode_varlen_mask.py:19
↓ 3 callersMethodforward(self, query, key, value, block_indices, cache_seqlens, block_table)
examples/blocksparse_attention/example_tilelang_sparse_gqa_decode_paged.py:185
↓ 3 callersFunctionget_ldmatrix_offset_b(
matrix: Literal["B"],
row_idx,
col_idx,
stride,
dtype: Literal["float16", "int8"] = "flo
tilelang/cuda/intrinsics/layout/mma_sp_layout.py:150