Module neuralops.attentions.kda_attention
Kernelized Decay Attention (KDA) / Recurrent Linear Attention (Corrected).
Implements multi-head linear recurrence with learned exponential decay gating, spherical normalization, denominator tracking, and pretrained weight transfer.
Functions
def apply_rotary_pos_emb(q: torch.Tensor,
k: torch.Tensor,
cos: torch.Tensor,
sin: torch.Tensor,
position_ids: torch.Tensor | None = None) ‑> tuple[torch.Tensor, torch.Tensor]-
Expand source code
def apply_rotary_pos_emb( q: torch.Tensor, k: torch.Tensor, cos: torch.Tensor, sin: torch.Tensor, position_ids: torch.Tensor | None = None, ) -> tuple[torch.Tensor, torch.Tensor]: if cos is None or sin is None: return q, k if cos.dim() == 2: cos = cos.unsqueeze(0).unsqueeze(0) sin = sin.unsqueeze(0).unsqueeze(0) elif cos.dim() == 3: cos = cos.unsqueeze(1) sin = sin.unsqueeze(1) while cos.dim() < q.dim(): cos = cos.unsqueeze(0) sin = sin.unsqueeze(0) rotary_dim = cos.shape[-1] head_dim = q.shape[-1] if rotary_dim < head_dim: q_rot, q_pass = q[..., :rotary_dim], q[..., rotary_dim:] k_rot, k_pass = k[..., :rotary_dim], k[..., rotary_dim:] # KDA-FIX-04: dtype-safe cast q_rot_embed = (q_rot * cos.to(q_rot.dtype)) + (_rotate_half(q_rot) * sin.to(q_rot.dtype)) k_rot_embed = (k_rot * cos.to(k_rot.dtype)) + (_rotate_half(k_rot) * sin.to(k_rot.dtype)) q = torch.cat([q_rot_embed, q_pass], dim=-1) k = torch.cat([k_rot_embed, k_pass], dim=-1) else: q = (q * cos.to(q.dtype)) + (_rotate_half(q) * sin.to(q.dtype)) k = (k * cos.to(k.dtype)) + (_rotate_half(k) * sin.to(k.dtype)) return q, k def inject_kda(layer: Any = None,
model: Any = None,
model_config: Any = None,
comp_config: Any = None,
layer_idx: int = 0,
total_layers: int = 12,
old_attn: nn.Module | None = None,
**kwargs: Any) ‑> KDAAttention | torch.nn.modules.module.Module | None-
Expand source code
@ATTENTION_REGISTRY.register("kda_inject") @ATTENTION_REGISTRY.register("inject_kda") def inject_kda( layer: Any = None, model: Any = None, model_config: Any = None, comp_config: Any = None, layer_idx: int = 0, total_layers: int = 12, old_attn: nn.Module | None = None, _depth: int = 0, **kwargs: Any, ) -> KDAAttention | nn.Module | None: if _depth > 8: logger.warning("inject_kda: max recursion depth exceeded, aborting.") return None target = layer if layer is not None else model if target is None: target = kwargs.get("model", kwargs.get("layer")) if target is None: return None cfg = model_config if cfg is None and hasattr(target, "config"): cfg = target.config # Whole-model traversal layer_list = None if hasattr(target, "distilbert") and hasattr(target.distilbert, "transformer"): layer_list = target.distilbert.transformer.layer elif hasattr(target, "roberta") and hasattr(target.roberta, "encoder"): layer_list = target.roberta.encoder.layer elif hasattr(target, "transformer") and hasattr(target.transformer, "h"): layer_list = target.transformer.h elif hasattr(target, "model") and hasattr(target.model, "layers"): layer_list = target.model.layers elif hasattr(target, "encoder") and hasattr(target.encoder, "layer"): layer_list = target.encoder.layer elif ( hasattr(target, "bert") and hasattr(target.bert, "encoder") and hasattr(target.bert.encoder, "layer") ): layer_list = target.bert.encoder.layer elif hasattr(target, "layers") and isinstance(target.layers, (nn.ModuleList, list)): layer_list = target.layers if layer_list is not None: num_injected = 0 tot = len(layer_list) for idx, lyr in enumerate(layer_list): res = inject_kda( layer=lyr, model_config=cfg, comp_config=comp_config, layer_idx=idx, total_layers=tot, _depth=_depth + 1, **kwargs, ) if res is not None: num_injected += 1 return target if num_injected > 0 else None # Single layer src_attn = old_attn if src_attn is None: if hasattr(target, "attention"): if hasattr(target.attention, "self"): src_attn = target.attention.self else: src_attn = target.attention elif hasattr(target, "self"): src_attn = target.self elif hasattr(target, "attn"): src_attn = target.attn elif hasattr(target, "self_attn"): src_attn = target.self_attn if src_attn is None and hasattr(target, "forward"): src_attn = target if src_attn is None and cfg is None: return None hidden_size = ( getattr(src_attn, "hidden_size", None) or getattr(src_attn, "embed_dim", None) or getattr(src_attn, "dim", None) or ( src_attn.q_proj.in_features if hasattr(src_attn, "q_proj") and hasattr(src_attn.q_proj, "in_features") else None ) or (getattr(target, "in_features", None) if target is not None else None) or getattr(cfg, "hidden_size", getattr(cfg, "dim", 768)) ) num_heads = ( getattr(src_attn, "num_heads", None) or getattr(src_attn, "num_attention_heads", None) or getattr(src_attn, "n_heads", None) or getattr(cfg, "num_attention_heads", getattr(cfg, "n_heads", 12)) ) try: new_attn = KDAAttention( config=cfg, comp_config=comp_config, d_model=hidden_size, num_heads=num_heads, old_attn=src_attn, hidden_size=hidden_size, num_attention_heads=num_heads, **kwargs, ) except Exception as e: logger.exception("KDA injection failed: %s", e) return None if target is not None: if hasattr(target, "attention"): if hasattr(target.attention, "self"): target.attention.self = new_attn new_attn.is_nested_encoder = True else: target.attention = new_attn elif hasattr(target, "self"): target.self = new_attn elif hasattr(target, "attn"): target.attn = new_attn elif hasattr(target, "self_attn"): target.self_attn = new_attn return new_attn
Classes
class KDAAttention (config: Any | None = None,
rank: int | None = None,
d_model: int | Any | None = None,
num_heads: int | None = None,
pretrained_attn: nn.Module | None = None,
old_attn: nn.Module | None = None,
comp_config: Any | None = None,
**kwargs: Any)-
Expand source code
@ATTENTION_REGISTRY.register("kda", supports_causal=True, supports_gqa=True) @ATTENTION_REGISTRY.register("kda_attention", supports_causal=True, supports_gqa=True) class KDAAttention(BaseAttention): is_custom_attention: bool = True def __init__( self, config: Any | None = None, rank: int | None = None, d_model: int | Any | None = None, num_heads: int | None = None, pretrained_attn: nn.Module | None = None, old_attn: nn.Module | None = None, comp_config: Any | None = None, **kwargs: Any, ) -> None: source_attn = pretrained_attn if pretrained_attn is not None else old_attn try: super().__init__(config, rank) except TypeError: super().__init__(config) # ---- hidden dim discovery ---- if d_model is None: d_model = kwargs.get("d_model") or kwargs.get("hidden_size") or kwargs.get("dim") if d_model is None: if config is not None: d_model = getattr(config, "hidden_size", getattr(config, "dim", 768)) elif source_attn is not None: out_layer = getattr( source_attn, "out_lin", getattr( source_attn, "dense", getattr( source_attn, "c_proj", getattr( source_attn, "o_proj", getattr(source_attn, "out_proj", None), ), ), ), ) if out_layer is not None: d_model = getattr( out_layer, "out_features", getattr(out_layer, "in_features", 768), ) else: q_l = getattr( source_attn, "q_proj", getattr( source_attn, "query", getattr(source_attn, "q_lin", None), ), ) d_model = ( getattr(q_l, "in_features", getattr(q_l, "out_features", 768)) if q_l is not None else 768 ) else: d_model = 768 if hasattr(d_model, "hidden_size"): d_model = d_model.hidden_size # ---- num heads ---- if num_heads is None: num_heads = kwargs.get("num_heads") or kwargs.get("num_attention_heads") if num_heads is None: if config is not None: num_heads = getattr( config, "num_attention_heads", getattr(config, "n_heads", 12) ) elif source_attn is not None: num_heads = getattr( source_attn, "num_attention_heads", getattr(source_attn, "n_heads", 12), ) else: num_heads = 12 self.dim = int(d_model) self.hidden_size = self.dim self.num_heads = int(num_heads) self.num_kv_heads = ( getattr( config, "num_key_value_heads", getattr(config, "num_kv_heads", self.num_heads), ) if config else self.num_heads ) self.head_dim = self.dim // self.num_heads if self.num_heads > 0 else 64 self.all_head_size = self.num_heads * self.head_dim self.all_kv_head_size = self.num_kv_heads * self.head_dim self.kv_repeat = max(1, self.num_heads // max(1, self.num_kv_heads)) self.supports_gqa = True # ---- decoder detection ---- model_type = getattr(config, "model_type", "").lower() if config else "" is_dec = ( getattr( config, "is_decoder", getattr(config, "is_causal", kwargs.get("is_causal", False)), ) if config else False ) _mt = (model_type or "").lower() _decoder_prefixes = ( "gpt", "qwen", "llama", "mistral", "gemma", "phi", "opt", "bloom", "falcon", "olmo", "mpt", "stablelm", ) if ( any(_mt.startswith(p) for p in _decoder_prefixes) or hasattr(config, "architectures") and any( "GPT" in str(a) or "CausalLM" in str(a) for a in (getattr(config, "architectures", []) or []) ) ): is_dec = True if kwargs.get("is_decoder", False) or kwargs.get("is_causal", False): is_dec = True self.is_decoder = bool(is_dec) self.is_causal = bool(is_dec) self.is_nested_encoder = False # ---- KDA-FIX-02: rename to lora_* prefix for framework recognition ---- # KDA-FIX-01: init at 5.0 → sigmoid(5) ≈ 0.9933 → effective context ~150 tokens self.lora_beta = nn.Parameter(torch.ones(self.num_heads, 1, 1) * 5.0) self.lora_output_scale = nn.Parameter(torch.ones(1)) # ---- LoRA config ---- if config is not None: self.lora_rank = getattr( config, "lora_rank", getattr(comp_config, "lora_rank", kwargs.get("lora_rank", 16)), ) elif comp_config is not None: self.lora_rank = getattr(comp_config, "lora_rank", kwargs.get("lora_rank", 16)) else: self.lora_rank = kwargs.get("lora_rank", 16) if config is not None: self.lora_alpha = getattr( config, "lora_alpha", getattr(comp_config, "lora_alpha", kwargs.get("lora_alpha", 32.0)), ) elif comp_config is not None: self.lora_alpha = getattr(comp_config, "lora_alpha", kwargs.get("lora_alpha", 32.0)) else: self.lora_alpha = kwargs.get("lora_alpha", 32.0) self.freeze_base = self.lora_rank > 0 self.rotary_emb = ( getattr(source_attn, "rotary_emb", None) if source_attn is not None else None ) # ---- projections ---- self.q_proj = LoRALinear( self.dim, self.all_head_size, bias=True, lora_rank=self.lora_rank, lora_alpha=self.lora_alpha, freeze_base=self.freeze_base, ) self.k_proj = LoRALinear( self.dim, self.all_kv_head_size, bias=True, lora_rank=self.lora_rank, lora_alpha=self.lora_alpha, freeze_base=self.freeze_base, ) self.v_proj = LoRALinear( self.dim, self.all_kv_head_size, bias=True, lora_rank=self.lora_rank, lora_alpha=self.lora_alpha, freeze_base=self.freeze_base, ) self.out_proj = LoRALinear( self.all_head_size, self.dim, bias=True, lora_rank=self.lora_rank, lora_alpha=self.lora_alpha, freeze_base=self.freeze_base, ) if source_attn is not None: self.copy_weights(source_attn) def freeze_base_weights(self) -> None: for mod in (self.q_proj, self.k_proj, self.v_proj, self.out_proj): if hasattr(mod, "freeze_base_weights"): mod.freeze_base_weights() # ------------------------------------------------------------------ # Weight transfer # ------------------------------------------------------------------ def copy_weights(self, src: Any) -> None: if src is None: return cls_name = getattr(src, "__class__", type(src)).__name__ has_out = ( hasattr(src, "dense") or hasattr(src, "out_proj") or hasattr(src, "out_lin") or hasattr(src, "c_proj") or hasattr(src, "o_proj") ) if cls_name in ("BertSelfAttention", "RobertaSelfAttention") or ( hasattr(src, "query") and not has_out ): self.is_nested_encoder = True if hasattr(src, "self") and hasattr(src, "output"): self.is_nested_encoder = True extracted: dict[str, tuple[torch.Tensor | None, torch.Tensor | None]] = { "q": (None, None), "k": (None, None), "v": (None, None), "o": (None, None), } # 1. GPT-2 fused c_attn if hasattr(src, "c_attn") and src.c_attn is not None: c_attn_mod = src.c_attn base_c = getattr(c_attn_mod, "base_layer", c_attn_mod) c_w = getattr(base_c, "weight", getattr(c_attn_mod, "weight", None)) if c_w is not None: c_w = c_w.data.clone() if ( c_attn_mod.__class__.__name__ == "Conv1D" or base_c.__class__.__name__ == "Conv1D" or hasattr(c_attn_mod, "nf") or (c_w.ndim == 2 and c_w.shape[0] < c_w.shape[1]) ): c_w = c_w.t() split_size = c_w.size(0) // 3 bias_mod = getattr(base_c, "bias", getattr(c_attn_mod, "bias", None)) c_b = bias_mod.data.clone() if bias_mod is not None else None extracted["q"] = ( c_w[:split_size, :], c_b[:split_size] if c_b is not None else None, ) extracted["k"] = ( c_w[split_size : 2 * split_size, :], c_b[split_size : 2 * split_size] if c_b is not None else None, ) extracted["v"] = ( c_w[2 * split_size :, :], c_b[2 * split_size :] if c_b is not None else None, ) if hasattr(src, "c_proj") and src.c_proj is not None: c_proj_mod = src.c_proj base_o = getattr(c_proj_mod, "base_layer", c_proj_mod) o_w = getattr(base_o, "weight", getattr(c_proj_mod, "weight", None)) if o_w is not None: o_w = o_w.data.clone() if ( c_proj_mod.__class__.__name__ == "Conv1D" or base_o.__class__.__name__ == "Conv1D" or hasattr(c_proj_mod, "nf") or (o_w.ndim == 2 and o_w.shape[0] < o_w.shape[1]) ): o_w = o_w.t() bias_o = getattr(base_o, "bias", getattr(c_proj_mod, "bias", None)) extracted["o"] = ( o_w, bias_o.data.clone() if bias_o is not None else None, ) # 2. RoBERTa nested elif hasattr(src, "self") and hasattr(src.self, "query"): s = src.self for proj_key, sub_name in [("q", "query"), ("k", "key"), ("v", "value")]: mod = getattr(s, sub_name, None) if mod is not None and hasattr(mod, "weight"): extracted[proj_key] = ( mod.weight.data.clone(), mod.bias.data.clone() if mod.bias is not None else None, ) if hasattr(src, "output") and hasattr(src.output, "dense"): out_mod = src.output.dense extracted["o"] = ( out_mod.weight.data.clone(), out_mod.bias.data.clone() if out_mod.bias is not None else None, ) # 3. Flat modules else: proj_candidates = { "q": ["q_lin", "q_proj", "query"], "k": ["k_lin", "k_proj", "key"], "v": ["v_lin", "v_proj", "value"], "o": ["out_lin", "out_proj", "dense", "o_proj"], } for proj_key, names in proj_candidates.items(): for name in names: if hasattr(src, name): mod = getattr(src, name) if mod is not None and hasattr(mod, "weight"): w_data = mod.weight.data.clone() if ( mod.__class__.__name__ == "Conv1D" or hasattr(mod, "nf") or ( w_data.ndim == 2 and proj_key == "o" and w_data.shape[0] < w_data.shape[1] ) ): w_data = w_data.t() extracted[proj_key] = ( w_data, mod.bias.data.clone() if mod.bias is not None else None, ) break missing = [ k for k, (w, _) in extracted.items() if w is None and (k != "o" or not self.is_nested_encoder) ] if missing: try: from neuralops.core.adapters import UniversalAdapter adapter = UniversalAdapter() for k in missing: w, b = adapter.get_weight_bias(src, k) if w is not None: extracted[k] = (w.clone(), b.clone() if b is not None else None) except Exception as e: logger.debug("UniversalAdapter fallback: %s", e) missing_after = [ k for k, (w, _) in extracted.items() if w is None and (k != "o" or not self.is_nested_encoder) ] if missing_after: raise RuntimeError( f"KDAAttention copy_weights failed: missing mandatory projections " f"{missing_after} from {src.__class__.__name__}." ) target_map = { "q": self.q_proj, "k": self.k_proj, "v": self.v_proj, "o": self.out_proj, } with torch.no_grad(): for proj_key, target_mod in target_map.items(): w, b = extracted[proj_key] if w is None: if proj_key == "o" and self.is_nested_encoder: nn.init.eye_(target_mod.weight) if target_mod.bias is not None: nn.init.zeros_(target_mod.bias) continue if w.ndim != 2: w = w.reshape(w.size(0), -1) if w.shape != target_mod.weight.shape and target_mod.weight.shape == w.t().shape: w = w.t() out_d = min(target_mod.weight.size(0), w.size(0)) in_d = min(target_mod.weight.size(1), w.size(1)) target_mod.weight.data[:out_d, :in_d].copy_( w[:out_d, :in_d].to( device=target_mod.weight.device, dtype=target_mod.weight.dtype ) ) if b is not None and target_mod.bias is not None: min_b = min(target_mod.bias.numel(), b.numel()) target_mod.bias.data[:min_b].copy_( b[:min_b].to(device=target_mod.bias.device, dtype=target_mod.bias.dtype) ) elif target_mod.bias is not None: nn.init.zeros_(target_mod.bias) w_norm = float(torch.norm(w[:out_d, :in_d]).item()) if w_norm < 1e-4: raise RuntimeError( f"KDAAttention weight verification failed for " f"'{proj_key}': norm too small ({w_norm:.2e})" ) if self.freeze_base: target_mod.freeze_base_weights() if self.lora_rank > 0 or self.freeze_base: self.freeze_base_weights() # ------------------------------------------------------------------ # KDA-FIX-03: chunked scan with bidirectional guard # ------------------------------------------------------------------ def _kda_scan_chunked( self, q: torch.Tensor, k: torch.Tensor, v: torch.Tensor, decay: torch.Tensor, mask: torch.Tensor | None = None, chunk_size: int = 256, _allow_bidirectional: bool = True, ) -> tuple[torch.Tensor, torch.Tensor | None]: B, H, L, d = q.shape gamma = decay.clamp(min=1e-4, max=1.0 - 1e-4) log_gamma = torch.log(gamma) mask_float = None if mask is not None: valid_m = get_token_valid_mask(mask, B, L, q.device) mask_float = valid_m.float() y_fwd_list = [] S = torch.zeros(B, H, d, v.shape[-1], device=q.device, dtype=torch.float32) Z = torch.zeros(B, H, d, 1, device=q.device, dtype=torch.float32) num_chunks = (L + chunk_size - 1) // chunk_size for c in range(num_chunks): start = c * chunk_size end = min(start + chunk_size, L) qc = q[:, :, start:end, :].float() kc = k[:, :, start:end, :].float() vc = v[:, :, start:end, :].float() Lc = end - start mc = None if mask_float is not None: mc = mask_float[:, start:end] mc_col = mc.unsqueeze(1).unsqueeze(-1) kc = kc * mc_col vc = vc * mc_col pos = torch.arange(Lc, device=q.device, dtype=torch.float32) pos_diff = pos.unsqueeze(-1) - pos.unsqueeze(-2) tril_mask = torch.tril(torch.ones(Lc, Lc, device=q.device, dtype=torch.bool)) D_intra = ( torch.exp( (pos_diff.unsqueeze(0).unsqueeze(0) * log_gamma).clamp(min=-40.0, max=0.0) ) * tril_mask.float() ) attn_intra = (qc @ kc.transpose(-1, -2)) * D_intra if mc is not None: mask_2d = mc.unsqueeze(1).unsqueeze(-1) * mc.unsqueeze(1).unsqueeze(-2) attn_intra = attn_intra * mask_2d num_intra = attn_intra @ vc den_intra = attn_intra.sum(dim=-1, keepdim=True) decay_inter = torch.exp( ((pos + 1).unsqueeze(0).unsqueeze(0).unsqueeze(-1) * log_gamma).clamp( min=-40.0, max=0.0 ) ) num_inter = (qc @ S) * decay_inter den_inter = (qc @ Z) * decay_inter if mc is not None: num_inter = num_inter * mc.unsqueeze(1).unsqueeze(-1) den_inter = den_inter * mc.unsqueeze(1).unsqueeze(-1) num_total = num_intra + num_inter den_total = (den_intra + den_inter).clamp(min=1e-4) yc = (num_total / den_total).to(q.dtype) if mc is not None: yc = yc * mc.unsqueeze(1).unsqueeze(-1) y_fwd_list.append(yc) decay_to_end = torch.exp( ((Lc - 1 - pos).unsqueeze(0).unsqueeze(0).unsqueeze(-1) * log_gamma).clamp( min=-40.0, max=0.0 ) ) k_decayed = kc * decay_to_end chunk_S = k_decayed.transpose(-1, -2) @ vc chunk_Z = k_decayed.transpose(-1, -2) @ torch.ones_like(vc[..., :1]) gamma_chunk = torch.exp((Lc * log_gamma).clamp(min=-40.0, max=0.0)) S = S * gamma_chunk + chunk_S Z = Z * gamma_chunk + chunk_Z y_fwd = torch.cat(y_fwd_list, dim=2) # KDA-FIX-03: guard against infinite recursion in bidirectional mode if (not self.is_decoder) and _allow_bidirectional: q_rev = q.flip(dims=[2]) k_rev = k.flip(dims=[2]) v_rev = v.flip(dims=[2]) mask_rev = mask_float.flip(dims=[-1]) if mask_float is not None else None y_bwd_rev, _ = self._kda_scan_chunked( q_rev, k_rev, v_rev, decay, mask_rev, chunk_size=chunk_size, _allow_bidirectional=False, ) y_bwd = y_bwd_rev.flip(dims=[2]) return y_fwd, y_bwd return y_fwd, None # ------------------------------------------------------------------ # Parallel scan (short sequences) # ------------------------------------------------------------------ def _kda_scan_parallel( self, q: torch.Tensor, k: torch.Tensor, v: torch.Tensor, decay: torch.Tensor, mask: torch.Tensor | None = None, ) -> tuple[torch.Tensor, torch.Tensor | None]: B, H, L, d = q.shape if L > 512: return self._kda_scan_chunked(q, k, v, decay, mask, chunk_size=256) log_decay = torch.log(decay.clamp(min=1e-4, max=1.0 - 1e-4)) pos = torch.arange(L, device=q.device, dtype=torch.float32) pos_diff = pos.unsqueeze(-1) - pos.unsqueeze(-2) tril_mask = torch.tril(torch.ones(L, L, device=q.device, dtype=torch.bool)) D_causal = ( torch.exp((pos_diff.unsqueeze(0).unsqueeze(0) * log_decay).clamp(min=-40.0, max=0.0)) * tril_mask.float() ) attn_scores = q.float() @ k.float().transpose(-1, -2) mask_2d = None if mask is not None: valid_m = get_token_valid_mask(mask, B, L, q.device) mask_float = valid_m.float() mask_2d = mask_float.unsqueeze(1).unsqueeze(-1) * mask_float.unsqueeze(1).unsqueeze(-2) D_causal = D_causal * mask_2d num_fwd = (attn_scores * D_causal) @ v.float() denom_fwd = (attn_scores * D_causal).sum(dim=-1, keepdim=True) y_fwd = torch.clamp( num_fwd / denom_fwd.clamp(min=1e-4), min=-1e4, max=1e4, ).to(q.dtype) if not self.is_decoder: triu_mask = torch.triu(torch.ones(L, L, device=q.device, dtype=torch.bool)) D_anti = ( torch.exp( (-pos_diff.unsqueeze(0).unsqueeze(0) * log_decay).clamp(min=-40.0, max=0.0) ) * triu_mask.float() ) if mask_2d is not None: D_anti = D_anti * mask_2d num_bwd = (attn_scores * D_anti) @ v.float() denom_bwd = (attn_scores * D_anti).sum(dim=-1, keepdim=True) y_bwd = torch.clamp( num_bwd / denom_bwd.clamp(min=1e-4), min=-1e4, max=1e4, ).to(q.dtype) return y_fwd, y_bwd return y_fwd, None # ------------------------------------------------------------------ # Forward # ------------------------------------------------------------------ def forward( self, hidden_states: torch.Tensor, attention_mask: torch.Tensor | None = None, head_mask: torch.Tensor | None = None, encoder_hidden_states: torch.Tensor | None = None, encoder_attention_mask: torch.Tensor | None = None, past_key_value: Any | None = None, output_attentions: bool | None = False, output_hidden_states: bool | None = False, return_dict: bool | None = True, position_embeddings: tuple[torch.Tensor, torch.Tensor] | None = None, *args: Any, **kwargs: Any, ) -> tuple[torch.Tensor, torch.Tensor | None]: if not hidden_states.is_contiguous(): hidden_states = hidden_states.contiguous() B, L, D = hidden_states.shape H, d = self.num_heads, self.head_dim q_raw = self.q_proj(hidden_states).view(B, L, H, d).transpose(1, 2).contiguous() k_raw = ( self.k_proj(hidden_states).view(B, L, self.num_kv_heads, d).transpose(1, 2).contiguous() ) v = self.v_proj(hidden_states).view(B, L, self.num_kv_heads, d).transpose(1, 2).contiguous() # RoPE if position_embeddings is not None: cos, sin = position_embeddings q_raw, k_raw = apply_rotary_pos_emb(q_raw, k_raw, cos, sin) elif self.rotary_emb is not None: rotary_module = self.rotary_emb pos_ids = kwargs.get("position_ids") if pos_ids is None: pos_ids = torch.arange(L, device=hidden_states.device).unsqueeze(0).expand(B, -1) try: cos, sin = rotary_module(q_raw, pos_ids) q_raw, k_raw = apply_rotary_pos_emb(q_raw, k_raw, cos, sin, position_ids=pos_ids) except Exception: try: cos, sin = rotary_module(q_raw, seq_len=L) q_raw, k_raw = apply_rotary_pos_emb( q_raw, k_raw, cos, sin, position_ids=pos_ids ) except Exception as e: logger.debug("KDA rotary_emb failed: %s", e) if self.kv_repeat > 1: k_raw = repeat_kv(k_raw, self.kv_repeat) v = repeat_kv(v, self.kv_repeat) q = F.elu(q_raw) + 1.0 k = (F.elu(k_raw) + 1.0) / (d**0.5) # KDA-FIX-01 + KDA-FIX-02: decay from lora_beta (trainable, init 5.0) decay = torch.sigmoid(self.lora_beta).view(1, H, 1, 1) mask_bool = None if attention_mask is not None: mask_bool = get_token_valid_mask(attention_mask, B, L, hidden_states.device) y_fwd, y_bwd = self._kda_scan_parallel(q, k, v, decay, mask_bool) if self.is_decoder or y_bwd is None: y = y_fwd else: y = 0.5 * (y_fwd + y_bwd) y = torch.nan_to_num(y, nan=0.0) if head_mask is not None: if head_mask.dim() == 1: hm = head_mask.view(1, -1, 1, 1) elif head_mask.dim() == 2: hm = head_mask.view(head_mask.size(0), -1, 1, 1) else: hm = head_mask y = y * hm out = y.transpose(1, 2).contiguous().view(B, L, self.all_head_size) # KDA-FIX-02: output_scale via lora_output_scale (trainable) out = out * self.lora_output_scale if self.is_nested_encoder: final_out = out else: final_out = self.out_proj(out) return final_out, NoneEvery custom attention module must inherit from this.
Initialize internal Module state, shared by both nn.Module and ScriptModule.
Ancestors
- BaseAttention
- torch.nn.modules.module.Module
Class variables
var is_custom_attention : bool-
The type of the None singleton.
Methods
def freeze_base_weights(self) ‑> None-
Expand source code
def freeze_base_weights(self) -> None: for mod in (self.q_proj, self.k_proj, self.v_proj, self.out_proj): if hasattr(mod, "freeze_base_weights"): mod.freeze_base_weights()
Inherited members
class LoRALinear (in_features: int,
out_features: int,
bias: bool = True,
lora_rank: int = 16,
lora_alpha: float = 32.0,
freeze_base: bool = False,
device: torch.device | None = None,
dtype: torch.dtype | None = None)-
Expand source code
class LoRALinear(nn.Module): def __init__( self, in_features: int, out_features: int, bias: bool = True, lora_rank: int = 16, lora_alpha: float = 32.0, freeze_base: bool = False, device: torch.device | None = None, dtype: torch.dtype | None = None, ) -> None: super().__init__() factory_kwargs = {"device": device, "dtype": dtype} self.in_features = in_features self.out_features = out_features self.lora_rank = lora_rank self.lora_alpha = lora_alpha self.lora_scaling = (lora_alpha / lora_rank) if lora_rank > 0 else 1.0 self.freeze_base = freeze_base self.weight = nn.Parameter(torch.empty((out_features, in_features), **factory_kwargs)) if bias: self.bias = nn.Parameter(torch.empty(out_features, **factory_kwargs)) else: self.register_parameter("bias", None) if self.lora_rank > 0: self.lora_A = nn.Parameter(torch.empty((lora_rank, in_features), **factory_kwargs)) self.lora_B = nn.Parameter(torch.empty((out_features, lora_rank), **factory_kwargs)) else: self.register_parameter("lora_A", None) self.register_parameter("lora_B", None) self.reset_parameters() if freeze_base: self.freeze_base_weights() def reset_parameters(self) -> None: nn.init.kaiming_uniform_(self.weight, a=math.sqrt(5)) if self.bias is not None: fan_in, _ = nn.init._calculate_fan_in_and_fan_out(self.weight) bound = 1 / math.sqrt(fan_in) if fan_in > 0 else 0 nn.init.uniform_(self.bias, -bound, bound) if self.lora_rank > 0 and self.lora_A is not None: nn.init.kaiming_uniform_(self.lora_A, a=math.sqrt(5)) self.lora_A.requires_grad = True if self.lora_rank > 0 and self.lora_B is not None: nn.init.zeros_(self.lora_B) self.lora_B.requires_grad = True def freeze_base_weights(self) -> None: self.weight.requires_grad = False if self.bias is not None: self.bias.requires_grad = False if self.lora_rank > 0 and self.lora_A is not None: self.lora_A.requires_grad = True if self.lora_rank > 0 and self.lora_B is not None: self.lora_B.requires_grad = True def unfreeze_base_weights(self) -> None: self.weight.requires_grad = True if self.bias is not None: self.bias.requires_grad = True def forward(self, x: torch.Tensor) -> torch.Tensor: out = F.linear(x, self.weight, self.bias) if self.lora_rank > 0 and self.lora_A is not None and self.lora_B is not None: lora_out = F.linear(F.linear(x, self.lora_A), self.lora_B) * self.lora_scaling out = out + lora_out return outBase class for all neural network modules.
Your models should also subclass this class.
Modules can also contain other Modules, allowing them to be nested in a tree structure. You can assign the submodules as regular attributes::
import torch.nn as nn import torch.nn.functional as F class Model(nn.Module): def __init__(self) -> None: super().__init__() self.conv1 = nn.Conv2d(1, 20, 5) self.conv2 = nn.Conv2d(20, 20, 5) def forward(self, x): x = F.relu(self.conv1(x)) return F.relu(self.conv2(x))Submodules assigned in this way will be registered, and will also have their parameters converted when you call :meth:
to, etc.Note
As per the example above, an
__init__()call to the parent class must be made before assignment on the child.:ivar training: Boolean represents whether this module is in training or evaluation mode. :vartype training: bool
Initialize internal Module state, shared by both nn.Module and ScriptModule.
Ancestors
- torch.nn.modules.module.Module
Methods
def forward(self, x: torch.Tensor) ‑> torch.Tensor-
Expand source code
def forward(self, x: torch.Tensor) -> torch.Tensor: out = F.linear(x, self.weight, self.bias) if self.lora_rank > 0 and self.lora_A is not None and self.lora_B is not None: lora_out = F.linear(F.linear(x, self.lora_A), self.lora_B) * self.lora_scaling out = out + lora_out return outDefine the computation performed at every call.
Should be overridden by all subclasses.
Note
Although the recipe for forward pass needs to be defined within this function, one should call the :class:
Moduleinstance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them. def freeze_base_weights(self) ‑> None-
Expand source code
def freeze_base_weights(self) -> None: self.weight.requires_grad = False if self.bias is not None: self.bias.requires_grad = False if self.lora_rank > 0 and self.lora_A is not None: self.lora_A.requires_grad = True if self.lora_rank > 0 and self.lora_B is not None: self.lora_B.requires_grad = True def reset_parameters(self) ‑> None-
Expand source code
def reset_parameters(self) -> None: nn.init.kaiming_uniform_(self.weight, a=math.sqrt(5)) if self.bias is not None: fan_in, _ = nn.init._calculate_fan_in_and_fan_out(self.weight) bound = 1 / math.sqrt(fan_in) if fan_in > 0 else 0 nn.init.uniform_(self.bias, -bound, bound) if self.lora_rank > 0 and self.lora_A is not None: nn.init.kaiming_uniform_(self.lora_A, a=math.sqrt(5)) self.lora_A.requires_grad = True if self.lora_rank > 0 and self.lora_B is not None: nn.init.zeros_(self.lora_B) self.lora_B.requires_grad = True def unfreeze_base_weights(self) ‑> None-
Expand source code
def unfreeze_base_weights(self) -> None: self.weight.requires_grad = True if self.bias is not None: self.bias.requires_grad = True