↓ 1 callersFunctioncompare_ab(baseline, target, b, s_q, cache_seqlens, h_q, h_kv, d, dv, causal, dtype)
examples/deepseek_mla/amd/benchmark_mla_decode_amd_aiter.py:123
↓ 1 callersFunctioncompare_ab(baseline, target, b, s_q, cache_seqlens, h_q, h_kv, d, dv, causal, dtype)
examples/deepseek_mla/amd/benchmark_mla_decode_amd_triton.py:342
↓ 1 callersFunctioncompile_int4_gemm(
M=1024,
N=1024,
K=1024,
block_M=128,
block_N=128,
block_K=64,
threads=128,
p
examples/gemm_int4/example_tilelang_gemm_int4.py:41
↓ 1 callersFunctionconstruct_inputs(batch_sizes_list, K, M, trans_b, padding_M, device, dtype)
examples/grouped_gemm/example_grouped_gemm_fwd.py:109
↓ 1 callersFunctionconstruct_inputs(batch_sizes_list, K, M, trans_b, padding_M, device, dtype)
examples/grouped_gemm/example_grouped_gemm_bwd.py:133
↓ 1 callersFunctionconstruct_inputs(batch_sizes_list, K, N, block_M, device, dtype)
examples/grouped_gemm/example_grouped_gemm_fwd_ptr.py:78
↓ 1 callersFunctionconvolution(data, kernel, S, D, P, block_M, block_N, block_K, num_stages, threads, dtype=T.float16, accum_dtype=T.float32
examples/convolution/example_convolution.py:20
↓ 1 callersFunctionconvolution_im2col(N, C, H, W, F, K, S, D, P, block_M, block_N, block_K, num_stages, threads, dtype=T.float16, accum_dtype=T.flo
testing/python/jit/test_tilelang_jit_tvm_ffi.py:319
↓ 1 callersFunctionconvolution_im2col(N, C, H, W, F, K, S, D, P, block_M, block_N, block_K, num_stages, threads, dtype=T.float16, accum_dtype=T.flo
testing/python/jit/test_tilelang_jit_nvrtc.py:321
↓ 1 callersMethodcreate(
cls, name: str, prim_func: PrimFunc[_P, _T], constexpr: set[Var], ir_gen: IRGenerator[_P, _T] | None
tilelang/language/eager/builder.py:1043
↓ 1 callersFunctioncummax_fragment_test(M, N, block_M, block_N, dim=0, reverse=False, dtype=T.float32)
testing/python/language/test_tilelang_language_scan.py:331
↓ 1 callersFunctioncummax_smem_out_test(M, N, block_M, block_N, dim=0, reverse=False, dtype=T.float32)
testing/python/language/test_tilelang_language_scan.py:349
↓ 1 callersFunctioncummax_smem_test(M, N, block_M, block_N, dim=0, reverse=False, dtype=T.float32)
testing/python/language/test_tilelang_language_scan.py:315
↓ 1 callersFunctioncumsum_fragment_test(M, N, block_M, block_N, dim=0, reverse=False, dtype=T.float32)
testing/python/language/test_tilelang_language_scan.py:31
↓ 1 callersFunctioncumsum_smem_test(M, N, block_M, block_N, dim=0, reverse=False, dtype=T.float32)
testing/python/language/test_tilelang_language_scan.py:14
↓ 1 callersFunctiondetect_iter_traitsDetect iter traits based on the pattern C[S, I, J] += A[S, I, K] * B[S, J, K] Parameters ---------- block : tirx.SBlock The block
tilelang/carver/matmul_analysis.py:237
↓ 1 callersFunctionelementwise_add(M, N, block_M, block_N, in_dtype, out_dtype, threads)
testing/python/language/test_tilelang_language_tma_1d.py:11
↓ 1 callersFunctionfast_flashattn(
batch,
heads,
seq_len,
dim,
is_causal,
groups,
block_M: int,
block_N: int,
examples/amd/example_amd_flash_attn_bwd.py:91
↓ 1 callersFunctionfast_flashattn(
batch,
heads,
seq_len,
dim,
is_causal,
groups,
block_M: int,
block_N: int,
examples/amd/example_amd_flash_attn_fwd.py:109