1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144
| def precompute_freqs_cis(dim: int, end: int, theta: float = 10000.0): freqs = 1.0 / (theta ** (torch.arange(0, dim, 2)[: (dim // 2)].float() / dim)) t = torch.arange(end, device=freqs.device, dtype=torch.float32) freqs = torch.outer(t, freqs) freqs_cis = torch.polar(torch.ones_like(freqs), freqs) return freqs_cis
def reshape_for_broadcast(freqs_cis: torch.Tensor, x: torch.Tensor): ndim = x.ndim assert 0 <= 1 < ndim assert freqs_cis.shape == (x.shape[1], x.shape[-1]) shape = [d if i == 1 or i == ndim - 1 else 1 for i, d in enumerate(x.shape)] return freqs_cis.view(*shape)
def apply_rotary_emb( xq: torch.Tensor, xk: torch.Tensor, freqs_cis: torch.Tensor, ) -> Tuple[torch.Tensor, torch.Tensor]: xq_ = torch.view_as_complex(xq.float().reshape(*xq.shape[:-1], -1, 2)) xk_ = torch.view_as_complex(xk.float().reshape(*xk.shape[:-1], -1, 2)) freqs_cis = reshape_for_broadcast(freqs_cis, xq_) xq_out = torch.view_as_real(xq_ * freqs_cis).flatten(3) xk_out = torch.view_as_real(xk_ * freqs_cis).flatten(3) return xq_out.type_as(xq), xk_out.type_as(xk)
class Attention(nn.Module): def __init__(self, args: ModelArgs): super().__init__() self.n_kv_heads = args.n_heads if args.n_kv_heads is None else args.n_kv_heads model_parallel_size = fs_init.get_model_parallel_world_size() self.n_local_heads = args.n_heads // model_parallel_size self.n_local_kv_heads = self.n_kv_heads // model_parallel_size self.n_rep = self.n_local_heads // self.n_local_kv_heads self.head_dim = args.dim // args.n_heads
self.wq = ColumnParallelLinear( args.dim, args.n_heads * self.head_dim, bias=False, gather_output=False, init_method=lambda x: x, ) self.wk = ColumnParallelLinear( args.dim, self.n_kv_heads * self.head_dim, bias=False, gather_output=False, init_method=lambda x: x, ) self.wv = ColumnParallelLinear( args.dim, self.n_kv_heads * self.head_dim, bias=False, gather_output=False, init_method=lambda x: x, ) self.wo = RowParallelLinear( args.n_heads * self.head_dim, args.dim, bias=False, input_is_parallel=True, init_method=lambda x: x, )
self.cache_k = torch.zeros( ( args.max_batch_size, args.max_seq_len, self.n_local_kv_heads, self.head_dim, ) ).cuda() self.cache_v = torch.zeros( ( args.max_batch_size, args.max_seq_len, self.n_local_kv_heads, self.head_dim, ) ).cuda()
def forward( self, x: torch.Tensor, start_pos: int, freqs_cis: torch.Tensor, mask: Optional[torch.Tensor], ): bsz, seqlen, _ = x.shape xq, xk, xv = self.wq(x), self.wk(x), self.wv(x)
xq = xq.view(bsz, seqlen, self.n_local_heads, self.head_dim) xk = xk.view(bsz, seqlen, self.n_local_kv_heads, self.head_dim) xv = xv.view(bsz, seqlen, self.n_local_kv_heads, self.head_dim)
xq, xk = apply_rotary_emb(xq, xk, freqs_cis=freqs_cis)
self.cache_k = self.cache_k.to(xq) self.cache_v = self.cache_v.to(xq)
self.cache_k[:bsz, start_pos : start_pos + seqlen] = xk self.cache_v[:bsz, start_pos : start_pos + seqlen] = xv
keys = self.cache_k[:bsz, : start_pos + seqlen] values = self.cache_v[:bsz, : start_pos + seqlen]
keys = repeat_kv( keys, self.n_rep ) values = repeat_kv( values, self.n_rep )
xq = xq.transpose(1, 2) keys = keys.transpose(1, 2) values = values.transpose( 1, 2 ) scores = torch.matmul(xq, keys.transpose(2, 3)) / math.sqrt(self.head_dim) if mask is not None: scores = scores + mask scores = F.softmax(scores.float(), dim=-1).type_as(xq) output = torch.matmul(scores, values) output = output.transpose(1, 2).contiguous().view(bsz, seqlen, -1) return self.wo(output)
|