Function_fwd_kernel(
Q,
K,
V,
sm_scale,
block_mask_ptr,
Out,
stride_qz,
stride_qh,
stride_qm,
benchmark/blocksparse_attention/benchmark_triton_block_sparse_fmha.py:93
Function_fwd_kernel(
Q,
K,
V,
sm_scale,
block_mask_ptr,
Out,
stride_qz,
stride_qh,
stride_qm,
examples/blocksparse_attention/block_sparse_attn_triton.py:93
Function_fwd_kernel(
Q,
K,
V,
sm_scale,
block_mask_ptr,
Out,
stride_qz,
stride_qh,
stride_qm,
examples/seer_attention/block_sparse_attn_triton.py:90
Function_merge_kernel(
o_partial_ptr,
lse_partial_ptr,
o_ptr,
lse_partial_stride_b,
lse_partial_stride_h,
l
examples/blocksparse_attention/example_triton_sparse_gqa_decode_varlen_mask.py:124
Function_merge_kernel(
o_partial_ptr,
lse_partial_ptr,
o_ptr,
lse_partial_stride_b,
lse_partial_stride_h,
l
examples/blocksparse_attention/example_triton_sparse_gqa_decode_varlen_indice.py:127
Function_mla_attn_kernel(
Q_nope,
Q_pe,
Kv_c_cache,
K_pe_cache,
Req_to_tokens,
B_seq_len,
O,
sm_scale,
examples/deepseek_mla/benchmark_mla.py:137
Function_mla_attn_kernel(
Q_nope,
Q_pe,
Kv_c_cache,
K_pe_cache,
Req_to_tokens,
B_seq_len,
O,
sm_scale,
examples/deepseek_mla/amd/benchmark_mla_decode_amd_triton.py:59
Function_mla_softmax_reducev_kernel(
Logits,
B_seq_len,
O,
stride_l_b,
stride_l_h,
stride_l_s,
stride_o_b,
stride
examples/deepseek_mla/benchmark_mla.py:276
Function_mla_softmax_reducev_kernel(
Logits,
B_seq_len,
O,
stride_l_b,
stride_l_h,
stride_l_s,
stride_o_b,
stride
examples/deepseek_mla/amd/benchmark_mla_decode_amd_triton.py:199