↓ 1 callersFunctionbitnet_158_int8xint2_decode(
M,
N,
K,
in_dtype,
out_dtype,
accum_dtype,
fast_decoding=True,
n_partition=4
examples/bitnet-1.58b/kernel_benchmark/tilelang_bitnet_158_int8xint2_decode.py:67
↓ 1 callersFunctionbitwise_reduce(
M,
N,
block_M,
block_N,
name,
func,
clear=True,
)
testing/python/math/test_math_bitwise_reduce.py:14
↓ 1 callersFunctionblocksparse_flashattn(batch, heads, seq_len, dim, downsample_len, is_causal)
benchmark/blocksparse_attention/benchmark_tilelang_block_sparse_fmha.py:34
↓ 1 callersFunctionblocksparse_flashattn(batch, heads, seq_len, dim, downsample_len, is_causal)
testing/python/transform/test_tilelang_transform_config_index_bitwidth.py:7
↓ 1 callersFunctionblocksparse_matmul(
A, B, BlockMask, block_M, block_N, block_K, num_stages, thread_num, enable_rasteration, dtype=T.float16,
examples/blocksparse_gemm/example_blocksparse_gemm.py:61
↓ 1 callersFunctionblocksparse_matmul(M, N, K, block_M, block_N, block_K, num_stages, dtype=T.float16, accum_dtype=T.float32)
testing/python/language/test_tilelang_language_pipeline.py:123
↓ 1 callersFunctionblocksparse_matmul_global(
M,
N,
K,
condition_dim,
block_M,
block_N,
block_K,
num_stages,
thread_nu
testing/python/language/test_tilelang_language_any_of.py:23
↓ 1 callersFunctionblocksparse_matmul_global(
M,
N,
K,
condition_dim,
block_M,
block_N,
block_K,
num_stages,
thread_nu
testing/python/language/test_tilelang_language_all_of.py:23
↓ 1 callersFunctionblocksparse_matmul_local(
M,
N,
K,
condition_dim,
block_M,
block_N,
block_K,
num_stages,
thread_nu
testing/python/language/test_tilelang_language_any_of.py:116
↓ 1 callersFunctionblocksparse_matmul_local(
M,
N,
K,
condition_dim,
block_M,
block_N,
block_K,
num_stages,
thread_nu
testing/python/language/test_tilelang_language_all_of.py:116
↓ 1 callersFunctionblocksparse_matmul_shared(
M,
N,
K,
condition_dim,
block_M,
block_N,
block_K,
num_stages,
thread_nu
testing/python/language/test_tilelang_language_any_of.py:67
↓ 1 callersFunctionblocksparse_matmul_shared(
M,
N,
K,
condition_dim,
block_M,
block_N,
block_K,
num_stages,
thread_nu
testing/python/language/test_tilelang_language_all_of.py:67
↓ 1 callersFunctionbuggy_matmul(A, B, block_M, block_N, block_K, dtype=T.float16, accum_dtype=T.float32)
examples/autodd/tilelang_minimized_expected.py:28
↓ 1 callersFunctionbuggy_matmul(A, B, block_M, block_N, block_K, dtype=T.float16, accum_dtype=T.float32)
examples/autodd/tilelang_buggy.py:118
↓ 1 callersFunctionbwd(
Q,
KV,
dO,
Indices,
Lse,
Delta,
Offsets,
TokenIndices,
H,
D,
D_t
examples/dsa_sparse_finetune/sparse_mla_bwd.py:83
↓ 1 callersFunctioncheck_int4_gemm_correctness(
M=1024,
N=1024,
K=1024,
block_M=128,
block_N=128,
block_K=64,
threads=128,
)
examples/gemm_int4/example_tilelang_gemm_int4.py:70
↓ 1 callersFunctionchunk_gla_fwd_o_gk(
q: torch.Tensor,
v: torch.Tensor,
g: torch.Tensor,
A: torch.Tensor,
h: torch.Tensor,
examples/kda/FLA_KDA/fla_chunk_o.py:299
↓ 1 callersFunctionchunk_kda_bwd_dqkwg(
q: torch.Tensor,
k: torch.Tensor,
w: torch.Tensor,
v: torch.Tensor,
h: torch.Tensor,
examples/kda/FLA_KDA/fla_chunk_inter.py:141
↓ 1 callersFunctionchunk_kda_fwd_inter_solve_fused(
q,
k,
gk,
beta,
Aqk,
Akk_diag,
Akk,
scale,
cu_seqlens: torch.LongTensor
examples/kda/FLA_KDA/fla_chunk_intra.py:611
↓ 1 callersFunctionchunk_retention_fwd_kernel(
B,
S,
H,
DK,
DV,
dtype: T.dtype = T.float16,
scale: float = None,
)
examples/linear_attention/example_retention_fwd.py:10
↓ 1 callersFunctionchunk_scan_fwd(
batch,
seqlen,
chunk_size,
ngroups,
nheads,
headdim,
dstate,
block_M=64,
benchmark/mamba2/benchmark_mamba_chunk_scan.py:190
↓ 1 callersFunctionchunk_scan_helion(cb, x, dt, dA_cumsum, C, states, D)
benchmark/mamba2/benchmark_mamba_chunk_scan.py:77
↓ 1 callersFunctionchunk_scan_triton(cb, x, dt, dA_cumsum, C, states, D)
benchmark/mamba2/benchmark_mamba_chunk_scan.py:72
↓ 1 callersFunctionclamp_within_bounds(
N,
block_N,
dtype,
min_val=None,
max_val=None,
)
testing/python/language/test_tilelang_language_clamp.py:5
↓ 1 callersFunctionclean_and_maintain_logits_(
Logits,
CuSeqLenKS,
CuSeqLenKE,
threads: int = 512,
block_K: int = 4096,
)
examples/dsa_hisa/clean_and_maintain_logits.py:10
↓ 1 callersFunctionclean_logits_(
Logits,
CuSeqLenKS,
CuSeqLenKE,
threads: int = 512,
block_K: int = 4096,
)
examples/deepseek_v32/fp8_lighting_indexer.py:176
↓ 1 callersFunctioncompare_ab(baseline, target, b, s_q, cache_seqlens, h_q, h_kv, d, dv, causal, dtype)
examples/deepseek_mla/benchmark_mla.py:457