↓ 1 callersFunctionmain(
BATCH: int = 8,
H: int = 32,
N_CTX: int = 1024,
D_HEAD: int = 64,
causal: bool = False,
examples/flash_attention/example_mha_bwd_bshd.py:298
↓ 1 callersFunctionmain(
Q: T.Tensor(q_shape, dtype),
K: T.Tensor(kv_shape, dtype),
V: T.Tensor(kv_shape, dty
examples/flash_attention/example_mha_fwd_bhsd.py:34
↓ 1 callersFunctionmain(BATCH: int = 1, H: int = 1, N_CTX: int = 512, D_HEAD: int = 128, window_size: Optional[int] = None, dtype: T.
examples/attention_sink/example_mha_sink_bwd_bhsd.py:431
↓ 1 callersFunctionmain(
batch: int = 1,
heads: int = 32,
seq_q: int = 256,
seq_kv: int = 256,
dim: int = 128,
examples/attention_sink/benchmark_gqa_sink_fwd.py:128
↓ 1 callersFunctionmain(
batch: int = 1,
heads: int = 32,
seq_q: int = 256,
seq_kv: int = 256,
dim: int = 128,
examples/attention_sink/benchmark_mha_sink_fwd.py:125
↓ 1 callersFunctionmain(
Q: T.Tensor(q_shape, dtype),
K: T.Tensor(kv_shape, dtype),
V: T.Tensor(kv_shape, dty
examples/attention_sink/example_mha_sink_fwd_bhsd.py:53
↓ 1 callersFunctionmain(
BATCH: int = 1,
H: int = 8,
N_CTX: int = 512,
D_HEAD: int = 64,
groups: int = 2,
win
examples/attention_sink/example_gqa_sink_bwd_bhsd.py:427
↓ 1 callersFunctionmain(
Q: T.Tensor(shape_q, dtype),
K: T.Tensor(shape_k, dtype),
V: T.Tensor(shape_v, dtype
examples/blocksparse_attention/example_tilelang_sparse_gqa_decode_varlen_indice.py:38
↓ 1 callersFunctionmain(batch=64, heads=32, heads_kv=8, max_cache_seqlen=8192, dim=128, dim_v=128, sparse_ratio=0.8, block_size=32)
examples/blocksparse_attention/example_triton_sparse_gqa_decode_varlen_mask.py:317
↓ 1 callersFunctionmain(
Q: T.Tensor(shape_q, dtype),
K: T.Tensor(shape_k, dtype),
V: T.Tensor(shape_v, dtype
examples/blocksparse_attention/example_tilelang_sparse_gqa_decode_paged.py:43
↓ 1 callersFunctionmain(
Q: T.Tensor(shape_q, dtype),
K: T.Tensor(shape_k, dtype),
V: T.Tensor(shape_v, dtype
examples/blocksparse_attention/example_tilelang_sparse_gqa_decode_varlen_mask.py:38
↓ 1 callersFunctionmain(batch=64, heads=32, heads_kv=8, max_cache_seqlen=8192, dim=128, dim_v=128, sparse_ratio=0.8, block_size=32)
examples/blocksparse_attention/example_triton_sparse_gqa_decode_varlen_indice.py:321
↓ 1 callersFunctionmain(
A: T.Tensor((M, K), T.int4),
B: T.Tensor((N, K), T.int4),
C: T.Tensor((M, N), T.int3
examples/gemm_int4/example_tilelang_gemm_int4.py:19
↓ 1 callersFunctionmain(batch=1, heads=64, kv_heads=1, kv_ctx=1024, dim=512, pe_dim=64)
examples/warp_specialize/example_warp_specialize_flashmla.py:352
↓ 1 callersFunctionmain(
M=1024,
N=1024,
K=1024,
accum_dtype=T.float,
e_dtype=T.int16,
block_M=128,
block
examples/gemm_sp/example_gemm_sp.py:45
↓ 1 callersFunctionmain(d_hidden=7168, d_expert=2048, n_routed_experts=8, n_shared_experts=1, n_experts_per_token=4, batch_size=1, se
examples/fusedmoe/example_fusedmoe_tilelang.py:476
↓ 1 callersFunctionmain(
Q: T.Tensor(q_shape, dtype),
K: T.Tensor(kv_shape, dtype),
V: T.Tensor(kv_shape, dty
examples/flash_attention_sm100/gqa_bwd_bshd.py:31
↓ 1 callersFunctionmain(
Q: T.Tensor(shape, dtype),
K: T.Tensor(shape, dtype),
V: T.Tensor(shape, dtype),
examples/flash_attention_sm100/mha_bwd_bshd.py:26
↓ 1 callersFunctionmain(
Q: T.Tensor(shape, dtype),
K: T.Tensor(shape, dtype),
V: T.Tensor(shape, dtype),
examples/flash_attention_sm100/mha_fwd_bshd.py:42
↓ 1 callersFunctionmain(
Q: T.Tensor(q_shape, dtype),
K: T.Tensor(kv_shape, dtype),
V: T.Tensor(kv_shape, dty
examples/flash_attention_sm100/gqa_fwd_bshd.py:45
↓ 1 callersFunctionmain(
A: T.Tensor((M, K), T.float4_e2m1fn),
B: T.Tensor((N, K), T.float8_e4m3fn),
SFA: T.T
examples/deepseek_v4/fp8_fp4_gemm_1d1d_sm100.py:40
↓ 1 callersFunctionmain(
batch=1,
heads=128,
kv_heads=1,
kv_ctx=8192,
dim=512,
pe_dim=64,
)
examples/deepseek_mla/example_mla_decode.py:218
↓ 1 callersFunctionmain(
batch=1,
heads=128,
kv_heads=1,
kv_ctx=8192,
dim=512,
pe_dim=64,
)
examples/deepseek_mla/example_mla_decode_ws.py:548
↓ 1 callersFunctionmake_matmul_prim(M, N, K, block_M=128, block_N=128, block_K=32, dtype=T.float16, accum_dtype=T.float32)
maint/host_checks/common.py:6
↓ 1 callersFunctionmake_mma_atom_kernel(M, N, K, in_dtype, out_dtype, accum_dtype)
testing/python/language/test_tilelang_language_atom_mma.py:47