↓ 3 callersFunctionmatmul(
M,
N,
K,
in_dtype,
out_dtype,
accum_dtype,
num_bits=4,
block_M=128,
bloc
examples/dequantize_gemm/example_dequant_gemm_fp4_hopper.py:110
↓ 3 callersFunctionmatmul(
M,
N,
K,
block_M,
block_N,
block_K,
trans_A,
trans_B,
in_dtype,
out_
testing/python/jit/test_tilelang_jit_cutedsl.py:22
↓ 3 callersFunctionmatmul(
M,
N,
K,
block_M,
block_N,
block_K,
trans_A,
trans_B,
in_dtype,
out_
testing/python/jit/test_tilelang_jit_tvm_ffi.py:9
↓ 3 callersFunctionmatmul(
M,
N,
K,
block_M,
block_N,
block_K,
trans_A,
trans_B,
in_dtype,
out_
testing/python/jit/test_tilelang_jit_nvrtc.py:9
↓ 3 callersFunctionmatmul_dynamic_mnk(
A,
B,
block_M,
block_N,
block_K,
trans_A,
trans_B,
in_dtype,
out_dtype,
examples/dynamic_shape/example_dynamic.py:6
↓ 3 callersFunctionmatmul_int8xint4(
M,
N,
K,
in_dtype,
out_dtype,
accum_dtype,
num_bits=4,
block_M=32,
block
examples/dequantize_gemm/example_dequant_gemm_w4a8.py:87
↓ 3 callersFunctionmqa_attn_return_logits_interface(q, kv, kv_scales, weights, cu_seqlen_ks, cu_seqlen_ke, clean_logits=True)
examples/deepseek_v32/fp8_lighting_indexer.py:205
↓ 3 callersFunctionprepare_output(
B,
S,
H,
DK,
DV,
chunk_size,
output_dtype,
gate_dtype,
state_dtype,
)
examples/gdn/example_wy_fast_bwd_split.py:77
↓ 3 callersFunctionref_program(A, B, BlockMask, block_M, block_N, block_K)
testing/python/language/test_tilelang_language_any_of.py:7
↓ 3 callersFunctionref_program(A, B, BlockMask, block_M, block_N, block_K)
testing/python/language/test_tilelang_language_all_of.py:7
↓ 3 callersFunctionrun_autotune(M, N, K, M_value=None, N_value=None, K_value=None, return_kernel=False)
testing/python/autotune/test_tilelang_autotune_eager_mode.py:93
↓ 3 callersFunctionrun_cutedsl_dynamic_shape(
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_cutedsl.py:320
↓ 3 callersFunctionrun_gemm(
M,
N,
K,
trans_A,
trans_B,
in_dtype,
out_dtype,
dtypeAccum,
block_M,
testing/python/amd/test_tilelang_test_amd.py:52
↓ 3 callersFunctionrun_nvrtc_dynamic_shape(
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:259
↓ 3 callersFunctionrun_tilelang_copy_fp4(M=1024, N=1024, block_M=128, block_N=128, src_dtype=T.float4_e2m1fn, dst_dtype=T.float4_e2m1fn)
testing/python/language/test_tilelang_language_copy.py:188
↓ 3 callersFunctionrun_tvm_ffi_dynamic_shape(
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:256
↓ 3 callersFunctionsparse_mla_bwd(q, kv, o, do, indices, lse, offsets, sm_scale=None, is_casual=True, return_kernel=False, delta=None)
examples/dsa_sparse_finetune/sparse_mla_bwd.py:254
↓ 3 callersFunctiontest_sparse_mla_fwd_pipelined(
B=1,
S=4096,
SKV=8192,
H=128,
HKV=1,
DQK=576,
DV=512,
topk=2048,
dtype=t
examples/deepseek_v32/sparse_mla_fwd_seesaw.py:591
↓ 3 callersFunctiontilelang_copy(M, N, block_M, block_N, src_dtype=T.float16, dst_dtype=T.float16)
testing/python/language/test_tilelang_language_copy.py:11