↓ 2 callersFunctionblock_sparse_flash_decode_gqa_indice_triton(
q,
k_cache,
v_cache,
cache_seqlens,
max_cache_seqlen,
max_selected_blocks,
block
examples/blocksparse_attention/example_triton_sparse_gqa_decode_varlen_indice.py:170
↓ 2 callersFunctionblock_sparse_flash_decode_gqa_mask_triton(
q,
k_cache,
v_cache,
cache_seqlens,
max_cache_seqlen,
block_mask,
block_size,
examples/blocksparse_attention/example_triton_sparse_gqa_decode_varlen_mask.py:167
↓ 2 callersFunctionblocksparse_flashattn(batch, heads, seq_len, dim, downsample_len, is_causal)
examples/blocksparse_attention/example_tilelang_block_sparse_attn.py:35
↓ 2 callersFunctionbwd(
Q,
KV,
dO,
Indices,
Lse,
Delta,
dKV,
H,
D,
D_tail,
topk,
kv_
examples/deepseek_v32/sparse_mla_bwd.py:77
↓ 2 callersFunctioncompare_a(target, b, s_q, cache_seqlens, h_q, h_kv, d, dv, causal, dtype)
examples/deepseek_mla/benchmark_mla.py:502
↓ 2 callersFunctioncompare_a(target, b, s_q, cache_seqlens, h_q, h_kv, d, dv, causal, dtype)
examples/deepseek_mla/amd/benchmark_mla_decode_amd_aiter.py:167
↓ 2 callersFunctioncompare_a(target, b, s_q, cache_seqlens, h_q, h_kv, d, dv, causal, dtype)
examples/deepseek_mla/amd/benchmark_mla_decode_amd_triton.py:386
↓ 2 callersFunctiondequantize_gemv(
M: int,
N: int,
K: int,
in_dtype: str,
out_dtype: str,
accum_dtype: str,
num_bit
examples/dequantize_gemm/example_dequant_gemv_fp16xint4.py:12
↓ 2 callersFunctionelementwise_add(A, B, block_M, block_N, in_dtype, out_dtype, threads)
examples/elementwise/example_elementwise_add.py:12
↓ 2 callersFunctionflashattn(batch, heads, seqlen_q, seqlen_kv, dim, is_causal, block_M, block_N)
examples/flash_decoding/example_mha_inference.py:12
↓ 2 callersFunctionflashattn(
batch, heads, k_heads, max_seqlen_kv, total_seqlen_k, dim, has_sink, block_N=128, block_H=64, num_split=
examples/flash_decoding/example_gqa_decode_varlen_logits.py:38
↓ 2 callersFunctionflashattn(batch, heads, heads_kv, dim, dim_v, block_N, block_H, num_stages, threads)
examples/blocksparse_attention/example_tilelang_sparse_gqa_decode_varlen_indice.py:19
↓ 2 callersFunctionflashattn(batch, heads, heads_kv, dim, dim_v, block_N, block_H, page_block_size, num_stages, threads, num_pages)
examples/blocksparse_attention/example_tilelang_sparse_gqa_decode_paged.py:21
↓ 2 callersFunctionflashattn(batch, heads, kv_head_num, seqlen_kv, dim, pe_dim, block_N, block_H, num_split, softmax_scale)
examples/deepseek_mla/example_mla_decode.py:14
↓ 2 callersFunctionflashattn_bwd(batch, heads, seq_len, dim, is_causal, block_M, block_N)
examples/flash_attention/example_mha_bwd_bhsd.py:158
↓ 2 callersFunctionflashattn_bwd(batch, heads, seq_len, dim, is_causal, block_M, block_N)
examples/flash_attention/example_mha_bwd_bshd.py:155
↓ 2 callersFunctionflashattn_bwd(
batch,
heads,
seq_len,
dim,
window_size=None, # None for full attention
sm_scale=No
examples/attention_sink/example_mha_sink_bwd_bhsd.py:203
↓ 2 callersFunctionflashattn_bwd(batch, heads, seq_len, dim, groups, window_size=None, sm_scale=None, dtype=T.float16)
examples/attention_sink/example_gqa_sink_bwd_bhsd.py:204
↓ 2 callersFunctionflashattn_bwd_preprocess(batch, heads, total_q, N_CTX, max_seq_len, dim_v)
examples/flash_attention/example_gqa_bwd_tma_reduce_varlen.py:143
↓ 2 callersFunctionflashattn_bwd_split(batch, heads, seq_len, dim_qk, dim_v, is_causal, block_M, block_N, threads=256, num_stages=2, groups=1)
examples/flash_attention/example_gqa_bwd.py:248
↓ 2 callersFunctionflashattn_bwd_split(
batch, total_q, total_kv, N_CTX, heads, max_seq_len, dim_qk, dim_v, is_causal, block_M, block_N, threads
examples/flash_attention/example_gqa_bwd_tma_reduce_varlen.py:366
↓ 2 callersFunctionflashattn_fwd(
batch,
heads,
seq_len,
dim,
window_size=None, # None for full attention,
sm_scale=N
examples/attention_sink/example_mha_sink_bwd_bhsd.py:28
↓ 2 callersFunctionflashattn_fwd(
batch,
heads,
seq_len,
dim,
groups=1,
window_size=None, # None for full attention
examples/attention_sink/example_gqa_sink_bwd_bhsd.py:26
↓ 2 callersFunctionflashmla_decode(batch, heads, kv_head_num, seqlen_kv, dim, pe_dim, block_N, block_H, num_split, threads=128)
examples/deepseek_mla/amd/benchmark_mla_decode_amd_tilelang.py:37
↓ 2 callersFunctiongemm_clc_persistent_2cta(
A,
B,
block_M,
block_N,
store_block_N,
block_K,
in_dtype,
out_dtype,
acc
examples/gemm_sm100/gemm_tcgen5mma_ws_clc.py:15
↓ 2 callersFunctiongemm_clc_persistent_2cta_pipelined_clc(
A,
B,
block_M,
block_N,
store_block_N,
block_K,
in_dtype,
out_dtype,
acc
examples/gemm_sm100/gemm_tcgen5mma_ws_clc.py:181