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_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(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(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(
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(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(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 = 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 = 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,
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(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(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(
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(
batch=1,
heads=128,
kv_heads=1,
kv_ctx=8192,
dim=512,
pe_dim=64,
)
examples/deepseek_mla/example_mla_decode.py:242
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