[claudesquad] update from 'add-llama-1' on 10 Jan 26 21:03 CST

nanovllm/models/__init__.py

@@ -0,0 +1,9 @@
+"""Model registry and model implementations."""
+
+from nanovllm.models.registry import register_model, get_model_class, MODEL_REGISTRY
+
+# Import models to trigger registration
+from nanovllm.models import qwen3
+from nanovllm.models import llama
+
+__all__ = ["register_model", "get_model_class", "MODEL_REGISTRY"]

nanovllm/models/llama.py

@@ -0,0 +1,194 @@
+import torch
+from torch import nn
+import torch.distributed as dist
+
+from nanovllm.layers.activation import SiluAndMul
+from nanovllm.layers.attention import Attention
+from nanovllm.layers.layernorm import RMSNorm
+from nanovllm.layers.linear import QKVParallelLinear, MergedColumnParallelLinear, RowParallelLinear
+from nanovllm.layers.rotary_embedding import get_rope
+from nanovllm.layers.embed_head import VocabParallelEmbedding, ParallelLMHead
+from nanovllm.models.registry import register_model
+
+
+class LlamaAttention(nn.Module):
+
+    def __init__(
+        self,
+        hidden_size: int,
+        num_heads: int,
+        num_kv_heads: int,
+        max_position: int = 4096 * 32,
+        head_dim: int | None = None,
+        rope_theta: float = 10000,
+        rope_scaling: dict | None = None,
+    ) -> None:
+        super().__init__()
+        tp_size = dist.get_world_size()
+        self.total_num_heads = num_heads
+        assert self.total_num_heads % tp_size == 0
+        self.num_heads = self.total_num_heads // tp_size
+        self.total_num_kv_heads = num_kv_heads
+        assert self.total_num_kv_heads % tp_size == 0
+        self.num_kv_heads = self.total_num_kv_heads // tp_size
+        self.head_dim = head_dim or hidden_size // self.total_num_heads
+        self.q_size = self.num_heads * self.head_dim
+        self.kv_size = self.num_kv_heads * self.head_dim
+        self.scaling = self.head_dim ** -0.5
+
+        self.qkv_proj = QKVParallelLinear(
+            hidden_size,
+            self.head_dim,
+            self.total_num_heads,
+            self.total_num_kv_heads,
+            bias=False,  # Llama has no attention bias
+        )
+        self.o_proj = RowParallelLinear(
+            self.total_num_heads * self.head_dim,
+            hidden_size,
+            bias=False,
+        )
+        self.rotary_emb = get_rope(
+            self.head_dim,
+            rotary_dim=self.head_dim,
+            max_position=max_position,
+            base=rope_theta,
+            rope_scaling=rope_scaling,
+        )
+        self.attn = Attention(
+            self.num_heads,
+            self.head_dim,
+            self.scaling,
+            self.num_kv_heads,
+        )
+
+    def forward(
+        self,
+        positions: torch.Tensor,
+        hidden_states: torch.Tensor,
+    ) -> torch.Tensor:
+        qkv = self.qkv_proj(hidden_states)
+        q, k, v = qkv.split([self.q_size, self.kv_size, self.kv_size], dim=-1)
+        q = q.view(-1, self.num_heads, self.head_dim)
+        k = k.view(-1, self.num_kv_heads, self.head_dim)
+        v = v.view(-1, self.num_kv_heads, self.head_dim)
+        # Llama has no q_norm/k_norm
+        q, k = self.rotary_emb(positions, q, k)
+        o = self.attn(q, k, v)
+        output = self.o_proj(o.flatten(1, -1))
+        return output
+
+
+class LlamaMLP(nn.Module):
+
+    def __init__(
+        self,
+        hidden_size: int,
+        intermediate_size: int,
+    ) -> None:
+        super().__init__()
+        self.gate_up_proj = MergedColumnParallelLinear(
+            hidden_size,
+            [intermediate_size] * 2,
+            bias=False,
+        )
+        self.down_proj = RowParallelLinear(
+            intermediate_size,
+            hidden_size,
+            bias=False,
+        )
+        self.act_fn = SiluAndMul()
+
+    def forward(self, x):
+        gate_up = self.gate_up_proj(x)
+        x = self.act_fn(gate_up)
+        x = self.down_proj(x)
+        return x
+
+
+class LlamaDecoderLayer(nn.Module):
+
+    def __init__(self, config) -> None:
+        super().__init__()
+        self.self_attn = LlamaAttention(
+            hidden_size=config.hidden_size,
+            num_heads=config.num_attention_heads,
+            num_kv_heads=config.num_key_value_heads,
+            max_position=config.max_position_embeddings,
+            head_dim=getattr(config, 'head_dim', None),
+            rope_theta=getattr(config, "rope_theta", 10000),
+            rope_scaling=getattr(config, "rope_scaling", None),
+        )
+        self.mlp = LlamaMLP(
+            hidden_size=config.hidden_size,
+            intermediate_size=config.intermediate_size,
+        )
+        self.input_layernorm = RMSNorm(config.hidden_size, eps=config.rms_norm_eps)
+        self.post_attention_layernorm = RMSNorm(config.hidden_size, eps=config.rms_norm_eps)
+
+    def forward(
+        self,
+        positions: torch.Tensor,
+        hidden_states: torch.Tensor,
+        residual: torch.Tensor | None,
+    ) -> tuple[torch.Tensor, torch.Tensor]:
+        if residual is None:
+            hidden_states, residual = self.input_layernorm(hidden_states), hidden_states
+        else:
+            hidden_states, residual = self.input_layernorm(hidden_states, residual)
+        hidden_states = self.self_attn(positions, hidden_states)
+        hidden_states, residual = self.post_attention_layernorm(hidden_states, residual)
+        hidden_states = self.mlp(hidden_states)
+        return hidden_states, residual
+
+
+class LlamaModel(nn.Module):
+
+    def __init__(self, config) -> None:
+        super().__init__()
+        self.embed_tokens = VocabParallelEmbedding(config.vocab_size, config.hidden_size)
+        self.layers = nn.ModuleList([LlamaDecoderLayer(config) for _ in range(config.num_hidden_layers)])
+        self.norm = RMSNorm(config.hidden_size, eps=config.rms_norm_eps)
+
+    def forward(
+        self,
+        input_ids: torch.Tensor,
+        positions: torch.Tensor,
+    ) -> torch.Tensor:
+        hidden_states = self.embed_tokens(input_ids)
+        residual = None
+        for layer in self.layers:
+            hidden_states, residual = layer(positions, hidden_states, residual)
+        hidden_states, _ = self.norm(hidden_states, residual)
+        return hidden_states
+
+
+@register_model("LlamaForCausalLM")
+class LlamaForCausalLM(nn.Module):
+    packed_modules_mapping = {
+        "q_proj": ("qkv_proj", "q"),
+        "k_proj": ("qkv_proj", "k"),
+        "v_proj": ("qkv_proj", "v"),
+        "gate_proj": ("gate_up_proj", 0),
+        "up_proj": ("gate_up_proj", 1),
+    }
+
+    def __init__(self, config) -> None:
+        super().__init__()
+        self.model = LlamaModel(config)
+        self.lm_head = ParallelLMHead(config.vocab_size, config.hidden_size)
+        if getattr(config, 'tie_word_embeddings', False):
+            self.lm_head.weight.data = self.model.embed_tokens.weight.data
+
+    def forward(
+        self,
+        input_ids: torch.Tensor,
+        positions: torch.Tensor,
+    ) -> torch.Tensor:
+        return self.model(input_ids, positions)
+
+    def compute_logits(
+        self,
+        hidden_states: torch.Tensor,
+    ) -> torch.Tensor:
+        return self.lm_head(hidden_states)

nanovllm/models/qwen3.py

@@ -9,6 +9,7 @@ from nanovllm.layers.layernorm import RMSNorm
 from nanovllm.layers.linear import QKVParallelLinear, MergedColumnParallelLinear, RowParallelLinear
 from nanovllm.layers.rotary_embedding import get_rope
 from nanovllm.layers.embed_head import VocabParallelEmbedding, ParallelLMHead
+from nanovllm.models.registry import register_model
 
 
 class Qwen3Attention(nn.Module):
@@ -186,6 +187,7 @@ class Qwen3Model(nn.Module):
         return hidden_states
 
 
+@register_model("Qwen3ForCausalLM", "Qwen2ForCausalLM")
 class Qwen3ForCausalLM(nn.Module):
     packed_modules_mapping = {
         "q_proj": ("qkv_proj", "q"),

nanovllm/models/registry.py

@@ -0,0 +1,46 @@
+"""Model registry for dynamic model loading."""
+
+from typing import Type
+from torch import nn
+
+# Global registry mapping architecture names to model classes
+MODEL_REGISTRY: dict[str, Type[nn.Module]] = {}
+
+
+def register_model(*architectures: str):
+    """
+    Decorator to register a model class for given architecture names.
+
+    Usage:
+        @register_model("LlamaForCausalLM")
+        class LlamaForCausalLM(nn.Module):
+            ...
+    """
+    def decorator(cls: Type[nn.Module]) -> Type[nn.Module]:
+        for arch in architectures:
+            MODEL_REGISTRY[arch] = cls
+        return cls
+    return decorator
+
+
+def get_model_class(hf_config) -> Type[nn.Module]:
+    """
+    Get model class based on HuggingFace config.
+
+    Args:
+        hf_config: HuggingFace model config with 'architectures' field
+
+    Returns:
+        Model class for the given architecture
+
+    Raises:
+        ValueError: If architecture is not supported
+    """
+    architectures = getattr(hf_config, "architectures", [])
+    for arch in architectures:
+        if arch in MODEL_REGISTRY:
+            return MODEL_REGISTRY[arch]
+    raise ValueError(
+        f"Unsupported architecture: {architectures}. "
+        f"Supported: {list(MODEL_REGISTRY.keys())}"
+    )