↓ 1 callersFunctionrun_matmul(M, N, K, block_M, block_N, block_K, dtype=T.float16, accum_dtype=T.float32)
testing/python/language/test_tilelang_language_clear.py:42
↓ 1 callersFunctionrun_matmul(M, N, K, block_M, block_N, block_K, dtype=T.float16, accum_dtype=T.float32)
testing/python/language/test_tilelang_language_alias.py:46
↓ 1 callersFunctionrun_matmul(M, N, K, block_M, block_N, block_K, dtype=T.float16, accum_dtype=T.float32)
testing/python/language/test_tilelang_language_ptr.py:112
↓ 1 callersFunctionrun_matmul_float_variable(M, N, K, block_M, block_N, block_K, trans_A, trans_B, in_dtype, out_dtype, dtypeAccum, num_stages, threads)
testing/python/jit/test_tilelang_jit_gemm_cython.py:478
↓ 1 callersFunctionrun_matmul_int_variable(M, N, K, block_M, block_N, block_K, trans_A, trans_B, in_dtype, out_dtype, dtypeAccum, num_stages, threads)
testing/python/jit/test_tilelang_jit_gemm_cython.py:407
↓ 1 callersFunctionrun_nvrtc_kernel_do_bench(
M, N, K, trans_A, trans_B, in_dtype, out_dtype, dtypeAccum, block_M, block_N, block_K, num_stages=3, num
testing/python/jit/test_tilelang_jit_nvrtc.py:176
↓ 1 callersFunctionrun_nvrtc_kernel_multi_stream(
M, N, K, trans_A, trans_B, in_dtype, out_dtype, dtypeAccum, block_M, block_N, block_K, num_stages=3, num
testing/python/jit/test_tilelang_jit_nvrtc.py:216
↓ 1 callersFunctionrun_pointer_table_grouped_matmul(batch_sizes_list, N, K, block_M, block_N, block_K, dtype=T.float16, accum_dtype=T.float32)
testing/python/language/test_tilelang_language_ptr.py:166
↓ 1 callersFunctionrun_test(
B,
S,
H,
DK,
DV,
chunk_size,
input_dtype,
output_dtype,
gate_dtype,
examples/gdn/example_wy_fast.py:134
↓ 1 callersFunctionrun_test(
B,
S,
H,
chunk_size,
reverse,
head_first,
input_dtype,
output_dtype,
thr
examples/gdn/example_cumsum.py:94
↓ 1 callersFunctionrun_test(
B,
S,
H,
DK,
DV,
input_dtype,
output_dtype,
accum_dtype,
gate_dtype,
examples/gdn/example_wy_fast_bwd_split.py:413
↓ 1 callersFunctionrun_test(
B,
S,
H,
DK,
DV,
input_dtype,
output_dtype,
accum_dtype,
gate_dtype,
examples/gdn/example_chunk_delta_h.py:228
↓ 1 callersFunctionrun_test(
B,
S,
H,
DK,
DV,
input_dtype,
output_dtype,
accum_dtype,
gate_dtype,
examples/gdn/example_chunk_delta_bwd.py:405
↓ 1 callersFunctionrun_test(
B,
S,
H,
DK,
DV,
chunk_size,
input_dtype,
output_dtype,
accum_dtype,
examples/gdn/example_chunk_o.py:153
↓ 1 callersFunctionrun_test(
B,
S,
H,
DK,
DV,
input_dtype,
output_dtype,
accum_dtype,
gate_dtype,
examples/gdn/example_chunk_o_bwd.py:362
↓ 1 callersFunctionrun_test(
B,
S,
H,
DK,
chunk_size,
input_dtype,
output_dtype,
accum_dtype,
use_g,
examples/gdn/example_chunk_scaled_dot_kkt.py:130
↓ 1 callersFunctionrun_test(
B,
S,
H,
DK,
scale,
input_dtype,
output_dtype,
accum_dtype,
gate_dtype,
examples/kda/chunk_inter_solve_fused.py:481
↓ 1 callersFunctionrun_test(
B,
S,
H,
DK,
scale,
input_dtype,
output_dtype,
accum_dtype,
gate_dtype,
examples/kda/chunk_intra_token_parallel.py:176
↓ 1 callersFunctionrun_test(
B,
S,
H,
DK,
DV,
input_dtype,
output_dtype,
accum_dtype,
gate_dtype,
examples/kda/wy_fast_bwd.py:241
↓ 1 callersFunctionrun_test(
B,
S,
H,
DK,
DV,
input_dtype,
output_dtype,
accum_dtype,
gate_dtype,
examples/kda/chunk_delta_bwd.py:203
↓ 1 callersFunctionrun_test(
B,
S,
H,
DK,
DV,
input_dtype,
output_dtype,
accum_dtype,
gate_dtype,
examples/kda/chunk_delta_h_fwd.py:185
↓ 1 callersFunctionrun_test(
B,
S,
H,
DK,
DV,
scale,
input_dtype,
gate_dtype,
qk_dtype,
chunk_siz
examples/kda/chunk_bwd_dqkwg.py:186
↓ 1 callersFunctionrun_test(
B,
S,
H,
DK,
DV,
chunk_size,
input_dtype,
output_dtype,
gate_dtype,
examples/kda/wy_fast.py:145
↓ 1 callersFunctionrun_test(
B,
S,
H,
DK,
DV,
chunk_size,
input_dtype,
output_dtype,
accum_dtype,
examples/kda/chunk_o.py:169
↓ 1 callersFunctionrun_test(
B,
S,
H,
DK,
input_dtype,
output_dtype,
accum_dtype,
gate_dtype,
state_d
examples/kda/chunk_bwd_intra.py:380
↓ 1 callersFunctionrun_test(
B,
S,
H,
DK,
DV,
scale,
input_dtype,
do_dtype,
da_dtype,
chunk_size,
examples/kda/chunk_bwd_gla_dA.py:95
↓ 1 callersFunctionrun_test(
B,
S,
H,
DK,
DV,
scale,
input_dtype,
do_dtype,
output_dtype,
chunk_s
examples/kda/chunk_bwd_dv.py:99
↓ 1 callersFunctionrun_test(M, N, K, block_M, block_N, block_K, dtype=T.float16, accum_dtype=T.float32)
testing/python/jit/test_tilelang_jit_nullptr.py:40
↓ 1 callersFunctionrun_tile_atomic_add(K, M, N, block_M, block_N, dtype=T.float32)
testing/python/language/test_tilelang_language_atomic.py:334
↓ 1 callersFunctionrun_tile_atomic_max(K, M, N, block_M, block_N, dtype=T.float32)
testing/python/language/test_tilelang_language_atomic.py:538
↓ 1 callersFunctionrun_tile_atomic_min(K, M, N, block_M, block_N, dtype=T.float32)
testing/python/language/test_tilelang_language_atomic.py:569
↓ 1 callersFunctionrun_tilelang_copy(M=1024, N=1024, block_M=128, block_N=128, dtype=T.float16, pad_value=0)
testing/python/language/test_tilelang_language_annotate_safe_value.py:29
↓ 1 callersFunctionrun_tilelang_copy_fp8_e8m0(M=1024, N=1024, block_M=128, block_N=128, src_dtype=T.float8_e8m0fnu, dst_dtype=T.float8_e8m0fnu)
testing/python/language/test_tilelang_language_copy.py:169
↓ 1 callersFunctionrun_tilelang_grouped_gemm(
batch_sizes_list,
K,
M,
block_M,
block_N,
block_K,
trans_b=False,
num_stages
examples/grouped_gemm/example_grouped_gemm_bwd.py:185
↓ 1 callersFunctionrun_tilelang_mla(q, block_table, blocked_k, max_seqlen_pad, block_size, b, s_q, cache_seqlens, h_q, h_kv, d, dv, causal, dtype
examples/deepseek_mla/example_mla_decode_paged.py:258
↓ 1 callersFunctionrun_torch_mla(q, block_table, blocked_k, max_seqlen_pad, block_size, b, s_q, cache_seqlens, h_q, h_kv, d, dv, causal, dtype
examples/deepseek_mla/example_mla_decode_paged.py:229
↓ 1 callersFunctionrun_tvm_ffi_kernel_do_bench(
M, N, K, trans_A, trans_B, in_dtype, out_dtype, dtypeAccum, block_M, block_N, block_K, num_stages=3, num
testing/python/jit/test_tilelang_jit_tvm_ffi.py:175
↓ 1 callersFunctionrun_tvm_ffi_kernel_multi_stream(
M, N, K, trans_A, trans_B, in_dtype, out_dtype, dtypeAccum, block_M, block_N, block_K, num_stages=3, num
testing/python/jit/test_tilelang_jit_tvm_ffi.py:214
↓ 1 callersFunctionscaled_dot_product_attention(query, key, value, h_q, h_kv, is_causal=False)
examples/deepseek_mla/example_mla_decode_paged.py:208
↓ 1 callersFunctionscaled_dot_product_attention(query, key, value, h_q, h_kv, is_causal=False)
examples/deepseek_mla/amd/benchmark_mla_decode_amd_aiter.py:20
↓ 1 callersFunctionscaled_dot_product_attention(query, key, value, h_q, h_kv, is_causal=False)
examples/deepseek_mla/amd/benchmark_mla_decode_amd_triton.py:11
↓ 1 callersFunctionshuffle_weight(
x: torch.Tensor,
layout=(16, 32),
k_pack=1,
is_transpose=False,
)
examples/gemm_fp8/example_tilelang_gemm_amd_fp8_preshuffle.py:150
↓ 1 callersFunctionsparse_mla_fwd(
Q,
KV,
Indices,
q_start_index_s,
heads,
dim,
tail_dim,
topk,
kv_stride,
examples/deepseek_v32/sparse_mla_fwd_seesaw.py:22
↓ 1 callersFunctionsparse_mla_fwd(
Q,
KV,
Indices,
Offsets,
TokenIndices,
heads,
dim,
tail_dim,
topk,
k
examples/dsa_sparse_finetune/sparse_mla_fwd.py:16
↓ 1 callersFunctionsparse_mla_fwd_interface(
q, kv, indices, q_start_index_s, kv_stride, sm_scale=None, is_casual=True, return_kernel=False, print_ke
examples/deepseek_v32/sparse_mla_fwd_pipelined.py:306
↓ 1 callersFunctionsparse_mla_fwd_interface(
q, kv, indices, q_start_index_s, kv_stride, sm_scale=None, is_casual=True, return_kernel=False, print_ke
examples/deepseek_v32/sparse_mla_fwd_seesaw.py:469