Methodforward(
ctx, q_unpad, k_unpad, v_unpad, sinks, cu_seqlens_q, cu_seqlens_k, N_CTX, max_seqlen_q, max_seqlen_k
examples/attention_sink/example_gqa_sink_bwd_varlen.py:503
Methodforward(ctx, q, k, v, sinks, window_size, groups)
examples/attention_sink/example_gqa_sink_bwd_bhsd.py:334
Methodforward(self, query, key, value, block_indices, cache_seqlens)
examples/blocksparse_attention/example_tilelang_sparse_gqa_decode_varlen_indice.py:172
Methodforward(self, query, key, value, block_mask, cache_seqlens)
examples/blocksparse_attention/example_tilelang_sparse_gqa_decode_varlen_mask.py:166
Methodforward(ctx, q, k, v, block_sparse_dense, sm_scale)
examples/blocksparse_attention/block_sparse_attn_triton.py:240
Functionfp8_gemm_kernel_(
A: T.Tensor[(M, K), FP8],
B: T.Tensor[(N, K), FP8],
C: T.Tensor[(M, N), out_dtype],
examples/deepseek_v32/inference/kernel.py:118
Functionfp8_index_kernel_(
q: T.Tensor[(b, m, h, d), FP8],
q_s: T.Tensor[(b, m, h), FP32],
k: T.Tensor[(b, n, d
examples/deepseek_v32/inference/kernel.py:201
Functionfunc(
A: T.Tensor((128,), T.float32),
B: T.Tensor((128,), T.float32),
)
testing/python/transform/test_tilelang_transform_lexical_alloc_scope.py:73
Functionfunc(X: T.Tensor((256, 256), T.float16), Y: T.Tensor((256, 256), T.float16))
testing/python/transform/test_tilelang_transform_inject_tcgen05_fence.py:98
Functionfunc(
A: T.Buffer([16, 16], "int32"),
B: T.Buffer([16, 16], "int32"),
C: T.Buffer([16, 16]
testing/python/transform/test_tilelang_transform_make_packed_api.py:168
Functionfunc(A: T.Buffer((128,), "float32"), B: T.Buffer((128,), "float32"))
testing/python/transform/test_tilelang_transform_lower_ldgstg.py:48
Functionfunc1(A: T.Tensor((M, N), T.float32), B: T.Tensor((M, N), T.float32))
testing/python/cache/test_tilelang_kernel_cache.py:227
Functionfunc2(A: T.Tensor((M, N), T.float32), B: T.Tensor((M, N), T.float32))
testing/python/cache/test_tilelang_kernel_cache.py:245
Functionfused_chunk_linear_attn_bwd(
Q: T.Tensor([B, S, H, DK], dtype), # type: ignore
K: T.Tensor([B, S, H, DK], dtype), # typ
examples/linear_attention/example_linear_attn_bwd.py:34
Functionfused_chunk_linear_attn_fwd(
Q: T.Tensor([B, S, H, DK], dtype), # type: ignore
K: T.Tensor([B, S, H, DK], dtype), # typ
examples/linear_attention/example_linear_attn_fwd.py:37
Functionfwd_main(KV: T.Tensor((M, N), dtype), ids: T.Tensor((4,), T.int32))
testing/python/issue/test_tilelang_issue_1210.py:10
Functionfwd_main(
KV: T.Tensor((M, N), dtype),
ids: T.Tensor((4,), "int32"),
ids2: T.Tensor((4,), "int
testing/python/issue/test_tilelang_issue_1263.py:9
Functiongemm(A, B, block_M, block_N, block_K, in_dtype, out_dtype, accum_dtype, num_stages, use_tma_store=True)
examples/gemm_sm100/gemm_tcgen5mma_ws.py:10
Functiongemm(
A: T.Tensor((M, K), dtype),
B: T.Tensor((K, N), dtype),
C: T.Tensor((M, N), dtype),
testing/python/profiler/test_tilelang_profiler_dynamic_symbolic.py:16
Functiongemm(
A: T.Tensor((M, K), dtype),
B: T.Tensor((K, N), dtype),
C: T.Tensor((M, N), dtype),
testing/python/profiler/test_tilelang_profiler.py:9
Functiongemm(
A: T.Tensor((M, K), dtype),
B: T.Tensor((K, N), dtype),
C: T.Tensor((M, N), dtype),
testing/python/language/test_tilelang_language_cluster.py:9
Functiongemm(
a: T.Tensor((M, K), "bfloat16"),
b: T.Tensor((K, N), "bfloat16"),
c: T.Tensor((M, N)
testing/python/issue/test_tilelang_issue_sm120_tma_smem_alignment.py:62
Functiongemm(
A: T.Tensor((M, K), dtype),
B: T.Tensor((K, N), dtype),
C: T.Tensor((M, N), dtype),
testing/python/metal/test_metal_codegen.py:11
Functiongemm(
A: T.Tensor((M, K), T.float16),
B: T.Tensor((K, N), T.float16),
C: T.Tensor((M, N),
testing/python/transform/test_tilelang_transform_pipeline_barrier_ownership.py:34
Functiongemm_2cta(A, B, block_M, block_N, block_K, in_dtype, out_dtype, accum_dtype, num_stages, use_tma_store=True)
examples/gemm_sm100/gemm_tcgen5mma_ws.py:73
Functiongemm_autotune(
A: T.Tensor((M, K), dtype),
B: T.Tensor((N, K), dtype),
C: T.Tensor((M, N), dtype),
examples/gemm/example_gemm_autotune.py:190
Functiongemm_autotune(
A: T.Tensor((M, K), dtype),
B: T.Tensor((N, K), dtype),
C: T.Tensor((M, N), dtype),
examples/gemm/example_gemm_advanced_autotune.py:248
Functiongemm_fp8_rs(
A: T.Tensor((M, K), dtype),
B: T.Tensor((N, K), dtype),
C: T.Tensor((M, N), accum_dt
examples/gemm_fp8/example_tilelang_gemm_amd.py:62
Functiongemm_fp8_ss(
A: T.Tensor((M, K), dtype),
B: T.Tensor((N, K), dtype),
C: T.Tensor((M, N), accum_dt
examples/gemm_fp8/example_tilelang_gemm_amd.py:81
Functiongemm_kernel(
A: T.Tensor((M, K), dtype),
B: T.Tensor((K, N), dtype),
C: T.Tensor((M, N), accum_dt
benchmark/matmul_metal/benchmark_matmul_metal.py:24