MCPcopy Create free account

hub / github.com/tile-ai/tilelang / functions

Functions7,254 in github.com/tile-ai/tilelang

Functionrun_kernel_only
()
examples/deepseek_v32/topk_selector.py:246
Functionrun_kernel_only
()
examples/deepseek_v32/sparse_mla_bwd.py:355
Functionrun_kernel_only
()
examples/minference/example_vertical_slash_sparse_attn.py:661
Functionrun_kernel_only
()
examples/dequantize_gemm/example_dequant_gemv_fp16xint4.py:271
Functionrun_kernel_only
()
examples/flash_attention/example_mha_bwd_bhsd.py:376
Functionrun_kernel_only
()
examples/flash_attention/example_mha_fwd_varlen.py:266
Functionrun_kernel_only
()
examples/flash_attention/example_gqa_bwd.py:525
Functionrun_kernel_only
()
examples/flash_attention/example_mha_bwd_bshd.py:371
Functionrun_kernel_only
()
examples/flash_attention/example_gqa_bwd_tma_reduce_varlen.py:734
Functionrun_kernel_only
()
examples/attention_sink/example_mha_sink_bwd_bhsd.py:524
Functionrun_kernel_only
()
examples/attention_sink/example_gqa_sink_bwd_bhsd.py:531
Functionrun_kernel_only
()
examples/blocksparse_attention/example_tilelang_sparse_gqa_decode_varlen_indice.py:406
Functionrun_kernel_only
()
examples/blocksparse_attention/example_tilelang_block_sparse_attn.py:194
Functionrun_kernel_only
()
examples/blocksparse_attention/example_tilelang_sparse_gqa_decode_paged.py:624
Functionrun_kernel_only
()
examples/blocksparse_attention/example_tilelang_sparse_gqa_decode_varlen_mask.py:446
Functionrun_kernel_only
()
examples/seer_attention/block_sparse_attn_tilelang.py:254
Functionrun_kernel_only2
()
examples/seer_attention/block_sparse_attn_tilelang.py:277
Functionrun_mla_aiter
(q, block_table, blocked_k, max_seqlen_pad, block_size, b, s_q, cache_seqlens, h_q, h_kv, d, dv, causal, dtype
examples/deepseek_mla/amd/benchmark_mla_decode_amd_aiter.py:68
Functionrun_once
()
examples/flash_decoding/example_gqa_decode_varlen_logits.py:275
Methodrun_once
(self, func: Callable | None = None)
tilelang/profiler/__init__.py:214
Functionrun_reference_fwd_bwd
()
examples/amd/example_amd_flash_attn_bwd.py:591
Functionrun_regression_perf
()
examples/gemv/example_gemv.py:360
Functionrun_regression_perf
(M: int = 4096, N: int = 4096, K: int = 4096)
examples/gemm/example_gemm_autotune.py:255
Functionrun_regression_perf
(M=4096, N=4096, K=4096)
examples/gemm/example_gemm_persistent.py:122
Functionrun_regression_perf
()
examples/gemm/example_gemm.py:60
Functionrun_regression_perf
(M=4096, N=4096, K=4096)
examples/gemm/example_gemm_intrinsics.py:180
Functionrun_regression_perf
(M: int = 4096, N: int = 4096, K: int = 4096)
examples/gemm/example_gemm_advanced_autotune.py:325
Functionrun_regression_perf
()
examples/deepseek_nsa/example_tilelang_nsa_fwd.py:185
Functionrun_regression_perf
()
examples/deepseek_nsa/example_tilelang_nsa_decode.py:174
Functionrun_regression_perf
()
examples/blocksparse_gemm/example_blocksparse_gemm.py:155
Functionrun_regression_perf
( B=1, S=4096, SKV=8192, H=128, HKV=1, DQK=576, DV=512, topk=2048, dtype=torch.bfloat16, block_I=64, num_s
examples/deepseek_v32/sparse_mla_fwd.py:275
Functionrun_regression_perf
(batch=64, seq_len=32 * 1024, topk=2048)
examples/deepseek_v32/topk_selector.py:238
Functionrun_regression_perf
(B=1, S=4096, SKV=8192, H=64, HKV=1, DQKV=576, DV=512, topk=2048, dtype=torch.bfloat16)
examples/deepseek_v32/sparse_mla_bwd.py:328
Functionrun_regression_perf
(S=4096, SKV=8192, H=32, HKV=1, D=64, kv_stride=1)
examples/deepseek_v32/fp8_lighting_indexer.py:277
Functionrun_regression_perf
(B=1, S=4096, SKV=8192, H=128, HKV=1, DQK=576, DV=512, topk=2048, dtype=torch.bfloat16, q_start_s_index=1024)
examples/deepseek_v32/sparse_mla_fwd_pipelined.py:467
Functionrun_regression_perf
(M=4096, N=4096, K=4096)
examples/dynamic_shape/example_dynamic.py:107
Functionrun_regression_perf
(B=1, S=1024, H=16, D=128)
examples/linear_attention/example_linear_attn_bwd.py:183
Functionrun_regression_perf
(B=1, S=512, H=16, D=128)
examples/linear_attention/example_linear_attn_fwd.py:137
Functionrun_regression_perf
(argv=None)
examples/convolution/example_convolution.py:82
Functionrun_regression_perf
( n: int = 128, c: int = 128, h: int = 64, w: int = 64, f: int = 128, k: int = 3,
examples/convolution/example_convolution_autotune.py:146
Functionrun_regression_perf
(batch=1, heads=1, seq_len=16384, head_dim=64, vertical_size=1000, slash_size=200)
examples/minference/example_vertical_slash_sparse_attn.py:603
Functionrun_regression_perf
()
examples/gemm_streamk/example_tilelang_gemm_streamk.py:174
Functionrun_regression_perf
()
examples/gemm_splitk/example_tilelang_gemm_splitk.py:51
Functionrun_regression_perf
()
examples/gemm_splitk/example_tilelang_gemm_splitk_vectorize_atomicadd.py:50
Functionrun_regression_perf
()
examples/dequantize_gemm/example_dequant_gemv_fp16xint4.py:220
Functionrun_regression_perf
(m=4096, n=4096, k=4096, scale_size=32, fast_dequant=True, with_bias=False)
examples/dequantize_gemm/example_dequant_gemm_bf16_mxfp4_hopper.py:539
Functionrun_regression_perf
(m=4096, n=4096, k=4096)
examples/dequantize_gemm/example_dequant_gemm_fp4_hopper.py:267
Functionrun_regression_perf
(m=4096, n=4096, k=4096, fast_dequant=True)
examples/dequantize_gemm/example_dequant_gemm_bf16_fp4_hopper.py:437
Functionrun_regression_perf
(m=4096, n=4096, k=4096)
examples/dequantize_gemm/example_dequant_gemm_w4a8.py:184
Functionrun_regression_perf
(BATCH=1, H=32, Q_CTX=128, KV_CTX=8192, D_HEAD=128, causal=False)
examples/flash_decoding/example_mha_inference.py:260
Functionrun_regression_perf
(batch: int = 1, heads: int = 32, groups: int = 8, kv_seqlen: int = 8192, dim: int = 128)
examples/flash_decoding/example_gqa_decode.py:446
Functionrun_regression_perf
(batch: int = 8, heads: int = 32, seq_len: int = 4096, dim: int = 128, is_causal: bool = False)
examples/flash_attention/example_mha_fwd_bshd.py:147
Functionrun_regression_perf
()
examples/flash_attention/example_mha_bwd_bhsd.py:351
Functionrun_regression_perf
( batch: int = 1, heads: int = 64, seq_len: int = 4096, dim: int = 128, is_causal: bool = False, groups: i
examples/flash_attention/example_gqa_fwd_bshd.py:198
Functionrun_regression_perf
(batch: int = 8, heads: int = 64, seq_len: int = 2048, dim: int = 128, causal: bool = False)
examples/flash_attention/example_mha_fwd_varlen.py:232
Functionrun_regression_perf
()
examples/flash_attention/example_gqa_bwd.py:487
Functionrun_regression_perf
()
examples/flash_attention/example_mha_bwd_bshd.py:346
Functionrun_regression_perf
()
examples/flash_attention/example_gqa_bwd_tma_reduce_varlen.py:688
Functionrun_regression_perf
( batch: int = 1, heads: int = 32, seq_q: int = 256, seq_kv: int = 256, dim: int = 64,
examples/flash_attention/example_mha_fwd_bhsd.py:158
Functionrun_regression_perf
( BATCH: int = 1, H: int = 32, N_CTX: int = 512, D_HEAD: int = 128, window_size: Optional[
examples/attention_sink/example_mha_sink_bwd_bhsd.py:491
Functionrun_regression_perf
( batch: int = 1, heads: int = 32, seq_q: int = 256, seq_kv: int = 256, dim: int = 128,
examples/attention_sink/example_mha_sink_fwd_bhsd.py:253
Functionrun_regression_perf
( 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:495
Functionrun_regression_perf
()
examples/elementwise/example_elementwise_add.py:44
Functionrun_regression_perf
(batch=8, 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_tilelang_sparse_gqa_decode_varlen_indice.py:375
Functionrun_regression_perf
()
examples/blocksparse_attention/example_tilelang_block_sparse_attn.py:179
Functionrun_regression_perf
(args)
examples/blocksparse_attention/example_tilelang_sparse_gqa_decode_paged.py:503
Functionrun_regression_perf
(batch=8, 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_tilelang_sparse_gqa_decode_varlen_mask.py:384
Functionrun_regression_perf
(M=8192, N=8192, blk_m=8)
examples/cast/example_per_token_cast_to_fp8.py:109
Functionrun_regression_perf
(M=8192, N=8192, BG=2, blk_m=8, batch_sizes=None)
examples/cast/example_group_per_split_token_cast_to_fp8.py:197
Functionrun_regression_perf
( n: int = 2048, hidden_size: int = 4096, hc_mult: int = 4, rms_eps: float = 1e-6, hc_pre_
examples/deepseek_mhc/example_mhc_pre.py:406
Functionrun_regression_perf
(n: int = 4096, h: int = 2560, hc_mult: int = 4)
examples/deepseek_mhc/example_mhc_post.py:108
Functionrun_regression_perf
(M=16384, N=16384, K=16384)
examples/warp_specialize/example_warp_specialize_gemm_barrierpipe_stage2.py:85
Functionrun_regression_perf
(M=16384, N=16384, K=16384)
examples/warp_specialize/example_warp_specialize_gemm_copy_1_gemm_0.py:74
Functionrun_regression_perf
(M=4096, N=4096, K=4096)
examples/warp_specialize/example_warp_specialize_gemm_copy_0_gemm_1.py:73
Functionrun_regression_perf
(M=16384, N=16384, K=16384)
examples/warp_specialize/example_warp_specialize_gemm_softpipe_stage2.py:76
Functionrun_regression_perf
( d_hidden=7168, d_expert=2048, n_routed_experts=8, n_shared_experts=1, n_experts_per_token=4, batch_size=
examples/fusedmoe/example_fusedmoe_tilelang.py:495
Functionrun_regression_perf
()
examples/seer_attention/block_sparse_attn_tilelang.py:235
Functionrun_regression_perf
(argv=None)
examples/topk/example_topk.py:85
Functionrun_regression_perf
( batch=1, heads=128, kv_heads=1, kv_ctx=8192, dim=512, pe_dim=64, )
examples/deepseek_mla/example_mla_decode.py:242
Functionrun_regression_perf
()
examples/gemm_fp8/example_tilelang_gemm_fp8_2xAcc.py:79
Functionrun_regression_perf
()
examples/gemm_fp8/example_tilelang_gemm_fp8.py:61
Functionrun_routed_kernel_only
()
examples/fusedmoe/example_fusedmoe_tilelang.py:590
Functionrun_shared_kernel_only
()
examples/fusedmoe/example_fusedmoe_tilelang.py:575
Methodrun_subprocess
(args)
tilelang/autodd.py:871
Functionrun_tilelang
()
examples/cast/example_per_token_cast_to_fp8.py:93
Functionrun_tilelang
()
examples/cast/example_group_per_split_token_cast_to_fp8.py:182
Functionrun_torch
()
examples/cast/example_per_token_cast_to_fp8.py:89
Functionrun_torch
()
examples/cast/example_group_per_split_token_cast_to_fp8.py:186
Functionrun_torch_mla
(q, block_table, blocked_k, max_seqlen_pad, block_size, b, s_q, cache_seqlens, h_q, h_kv, d, dv, causal, dtype
examples/deepseek_mla/benchmark_mla.py:36
Functionrun_torch_mla
(q, block_table, blocked_k, max_seqlen_pad, block_size, b, s_q, cache_seqlens, h_q, h_kv, d, dv, causal, dtype
examples/deepseek_mla/amd/benchmark_mla_decode_amd_aiter.py:41
Functionrun_torch_mla
(q, block_table, blocked_k, max_seqlen_pad, block_size, b, s_q, cache_seqlens, h_q, h_kv, d, dv, causal, dtype
examples/deepseek_mla/amd/benchmark_mla_decode_amd_triton.py:32
Functionrun_triton
()
examples/cast/example_per_token_cast_to_fp8.py:97
Functionrun_with_timeout
Run ``func`` under a deadline, raising :class:`TimeoutException` if exceeded. Picks the strongest available primitive: * **POSIX, main threa
tilelang/autotuner/tuner.py:150
Methodrval
(self, name: str, value: Any)
tilelang/language/eager/ast.py:238
Methodrval
(self, name: str, value: Any)
tilelang/language/eager/builder.py:699
Functionsample_kernel
( num_blocks: T.int32, idx_out: T.Tensor[(32,), T.int32], )
testing/python/language/test_tilelang_language_frontend_v2.py:414
Functionsample_kernel
(global_tensor: T.Tensor[(length,), T.int32])
testing/python/issue/test_tilelang_issue_1237.py:13
Functionsample_kernel
(x: T.Tensor[(m,), T.int32])
testing/python/transform/test_nullable_buffer_params.py:84
Methodsave_vocabulary
Save the vocabulary and special tokens file to a directory. Args: save_directory (`str`): The directory
examples/bitnet-1.58b/tokenization_bitnet.py:315
Functionscalar_buffer_layout_fn
(i, j, rep)
testing/python/layout/test_tilelang_layout_inference.py:41
← previousnext →5,601–5,700 of 7,254, ranked by callers