[Model] use AutoWeightsLoader for deepseek_v2, internlm2 (#16383)

Signed-off-by: Aaron Ang <aaron.angyd@gmail.com>

vllm/model_executor/models/deepseek_v2.py

@@ -53,7 +53,7 @@ from vllm.model_executor.sampling_metadata import SamplingMetadata
 from vllm.sequence import IntermediateTensors
 
 from .interfaces import SupportsPP
-from .utils import (PPMissingLayer, is_pp_missing_parameter,
+from .utils import (AutoWeightsLoader, PPMissingLayer, is_pp_missing_parameter,
                     make_empty_intermediate_tensors_factory, make_layers,
                     maybe_prefix)
 
@@ -668,6 +668,91 @@ class DeepseekV2Model(nn.Module):
         hidden_states, _ = self.norm(hidden_states, residual)
         return hidden_states
 
+    def load_weights(self, weights: Iterable[Tuple[str,
+                                                   torch.Tensor]]) -> Set[str]:
+        stacked_params_mapping = [
+            # (param_name, shard_name, shard_id)
+            ("gate_up_proj", "gate_proj", 0),
+            ("gate_up_proj", "up_proj", 1),
+        ]
+
+        # Params for weights, fp8 weight scales, fp8 activation scales
+        # (param_name, weight_name, expert_id, shard_id)
+        expert_params_mapping = FusedMoE.make_expert_params_mapping(
+            ckpt_gate_proj_name="gate_proj",
+            ckpt_down_proj_name="down_proj",
+            ckpt_up_proj_name="up_proj",
+            num_experts=self.config.n_routed_experts)
+
+        params_dict = dict(self.named_parameters())
+        loaded_params: Set[str] = set()
+        for name, loaded_weight in weights:
+            spec_layer = get_spec_layer_idx_from_weight_name(self.config, name)
+            if spec_layer is not None:
+                continue  # skip spec decode layers for main model
+
+            for (param_name, weight_name, shard_id) in stacked_params_mapping:
+                # Skip non-stacked layers and experts (experts handled below).
+                if weight_name not in name:
+                    continue
+                # We have mlp.experts[0].gate_proj in the checkpoint.
+                # Since we handle the experts below in expert_params_mapping,
+                # we need to skip here BEFORE we update the name, otherwise
+                # name will be updated to mlp.experts[0].gate_up_proj, which
+                # will then be updated below in expert_params_mapping
+                # for mlp.experts[0].gate_gate_up_proj, which breaks load.
+                if (("mlp.experts." in name) and name not in params_dict):
+                    continue
+                name = name.replace(weight_name, param_name)
+                # Skip loading extra bias for GPTQ models.
+                if name.endswith(".bias") and name not in params_dict:
+                    continue
+
+                if is_pp_missing_parameter(name, self):
+                    continue
+
+                param = params_dict[name]
+                weight_loader = param.weight_loader
+                weight_loader(param, loaded_weight, shard_id)
+                break
+            else:
+                for mapping in expert_params_mapping:
+                    param_name, weight_name, expert_id, shard_id = mapping
+                    if weight_name not in name:
+                        continue
+                    name = name.replace(weight_name, param_name)
+
+                    if is_pp_missing_parameter(name, self):
+                        continue
+
+                    param = params_dict[name]
+                    weight_loader = param.weight_loader
+                    weight_loader(param,
+                                  loaded_weight,
+                                  name,
+                                  shard_id=shard_id,
+                                  expert_id=expert_id)
+                    break
+                else:
+                    # Skip loading extra bias for GPTQ models.
+                    if name.endswith(".bias") and name not in params_dict:
+                        continue
+
+                    # Remapping the name of FP8 kv-scale.
+                    name = maybe_remap_kv_scale_name(name, params_dict)
+                    if name is None:
+                        continue
+
+                    if is_pp_missing_parameter(name, self):
+                        continue
+
+                    param = params_dict[name]
+                    weight_loader = getattr(param, "weight_loader",
+                                            default_weight_loader)
+                    weight_loader(param, loaded_weight)
+            loaded_params.add(name)
+        return loaded_params
+
 
 class DeepseekV2ForCausalLM(nn.Module, SupportsPP):
 
@@ -737,91 +822,8 @@ class DeepseekV2ForCausalLM(nn.Module, SupportsPP):
 
     def load_weights(self, weights: Iterable[Tuple[str,
                                                    torch.Tensor]]) -> Set[str]:
-        stacked_params_mapping = [
+        loader = AutoWeightsLoader(self, skip_prefixes=["rotary_emb.inv_freq"])
-            # (param_name, shard_name, shard_id)
+        return loader.load_weights(weights)
-            ("gate_up_proj", "gate_proj", 0),
-            ("gate_up_proj", "up_proj", 1),
-        ]
-
-        # Params for weights, fp8 weight scales, fp8 activation scales
-        # (param_name, weight_name, expert_id, shard_id)
-        expert_params_mapping = FusedMoE.make_expert_params_mapping(
-            ckpt_gate_proj_name="gate_proj",
-            ckpt_down_proj_name="down_proj",
-            ckpt_up_proj_name="up_proj",
-            num_experts=self.config.n_routed_experts)
-
-        params_dict = dict(self.named_parameters())
-        loaded_params: Set[str] = set()
-        for name, loaded_weight in weights:
-            if "rotary_emb.inv_freq" in name:
-                continue
-
-            spec_layer = get_spec_layer_idx_from_weight_name(self.config, name)
-            if spec_layer is not None:
-                continue  # skip spec decode layers for main model
-
-            for (param_name, weight_name, shard_id) in stacked_params_mapping:
-                # Skip non-stacked layers and experts (experts handled below).
-                if weight_name not in name:
-                    continue
-                # We have mlp.experts[0].gate_proj in the checkpoint.
-                # Since we handle the experts below in expert_params_mapping,
-                # we need to skip here BEFORE we update the name, otherwise
-                # name will be updated to mlp.experts[0].gate_up_proj, which
-                # will then be updated below in expert_params_mapping
-                # for mlp.experts[0].gate_gate_up_proj, which breaks load.
-                if (("mlp.experts." in name) and name not in params_dict):
-                    continue
-                name = name.replace(weight_name, param_name)
-                # Skip loading extra bias for GPTQ models.
-                if name.endswith(".bias") and name not in params_dict:
-                    continue
-
-                if is_pp_missing_parameter(name, self):
-                    continue
-
-                param = params_dict[name]
-                weight_loader = param.weight_loader
-                weight_loader(param, loaded_weight, shard_id)
-                break
-            else:
-                for mapping in expert_params_mapping:
-                    param_name, weight_name, expert_id, shard_id = mapping
-                    if weight_name not in name:
-                        continue
-                    name = name.replace(weight_name, param_name)
-
-                    if is_pp_missing_parameter(name, self):
-                        continue
-
-                    param = params_dict[name]
-                    weight_loader = param.weight_loader
-                    weight_loader(param,
-                                  loaded_weight,
-                                  name,
-                                  shard_id=shard_id,
-                                  expert_id=expert_id)
-                    break
-                else:
-                    # Skip loading extra bias for GPTQ models.
-                    if name.endswith(".bias") and name not in params_dict:
-                        continue
-
-                    # Remapping the name of FP8 kv-scale.
-                    name = maybe_remap_kv_scale_name(name, params_dict)
-                    if name is None:
-                        continue
-
-                    if is_pp_missing_parameter(name, self):
-                        continue
-
-                    param = params_dict[name]
-                    weight_loader = getattr(param, "weight_loader",
-                                            default_weight_loader)
-                    weight_loader(param, loaded_weight)
-            loaded_params.add(name)
-        return loaded_params
 
 
 class DeepseekV3ForCausalLM(DeepseekV2ForCausalLM):

vllm/model_executor/models/internlm2.py

@@ -32,7 +32,7 @@ from vllm.model_executor.sampling_metadata import SamplingMetadata
 from vllm.sequence import IntermediateTensors, PoolerOutput
 
 from .interfaces import SupportsLoRA, SupportsPP
-from .utils import (is_pp_missing_parameter,
+from .utils import (AutoWeightsLoader, is_pp_missing_parameter,
                     make_empty_intermediate_tensors_factory, make_layers,
                     maybe_prefix)
 
@@ -306,6 +306,42 @@ class InternLM2Model(nn.Module):
         hidden_states, _ = self.norm(hidden_states, residual)
         return hidden_states
 
+    def load_weights(self, weights: Iterable[Tuple[str,
+                                                   torch.Tensor]]) -> Set[str]:
+        stacked_params_mapping = [
+            # (param_name, shard_name, shard_id)
+            ("gate_up_proj", "w1", 0),
+            ("gate_up_proj", "w3", 1),
+        ]
+        params_dict = dict(self.named_parameters())
+        loaded_params: Set[str] = set()
+        for name, loaded_weight in weights:
+            for (param_name, weight_name, shard_id) in stacked_params_mapping:
+                if weight_name not in name:
+                    continue
+                name = name.replace(weight_name, param_name)
+                # Skip loading extra bias for GPTQ models.
+                if name.endswith(".bias") and name not in params_dict:
+                    continue
+                if is_pp_missing_parameter(name, self):
+                    continue
+                param = params_dict[name]
+                weight_loader = param.weight_loader
+                weight_loader(param, loaded_weight, shard_id)
+                break
+            else:
+                # Skip loading extra bias for GPTQ models.
+                if name.endswith(".bias") and name not in params_dict:
+                    continue
+                if is_pp_missing_parameter(name, self):
+                    continue
+                param = params_dict[name]
+                weight_loader = getattr(param, "weight_loader",
+                                        default_weight_loader)
+                weight_loader(param, loaded_weight)
+            loaded_params.add(name)
+        return loaded_params
+
 
 class InternLM2ForCausalLM(nn.Module, SupportsPP, SupportsLoRA):
     packed_modules_mapping = {
@@ -373,41 +409,8 @@ class InternLM2ForCausalLM(nn.Module, SupportsPP, SupportsLoRA):
 
     def load_weights(self, weights: Iterable[Tuple[str,
                                                    torch.Tensor]]) -> Set[str]:
-        stacked_params_mapping = [
+        loader = AutoWeightsLoader(self, skip_prefixes=["rotary_emb.inv_freq"])
-            # (param_name, shard_name, shard_id)
+        return loader.load_weights(weights)
-            ("gate_up_proj", "w1", 0),
-            ("gate_up_proj", "w3", 1),
-        ]
-        params_dict = dict(self.named_parameters())
-        loaded_params: Set[str] = set()
-        for name, loaded_weight in weights:
-            if "rotary_emb.inv_freq" in name:
-                continue
-            for (param_name, weight_name, shard_id) in stacked_params_mapping:
-                if weight_name not in name:
-                    continue
-                name = name.replace(weight_name, param_name)
-                # Skip loading extra bias for GPTQ models.
-                if name.endswith(".bias") and name not in params_dict:
-                    continue
-                if is_pp_missing_parameter(name, self):
-                    continue
-                param = params_dict[name]
-                weight_loader = param.weight_loader
-                weight_loader(param, loaded_weight, shard_id)
-                break
-            else:
-                # Skip loading extra bias for GPTQ models.
-                if name.endswith(".bias") and name not in params_dict:
-                    continue
-                if is_pp_missing_parameter(name, self):
-                    continue
-                param = params_dict[name]
-                weight_loader = getattr(param, "weight_loader",
-                                        default_weight_loader)
-                weight_loader(param, loaded_weight)
-            loaded_params.add(name)
-        return loaded_params
 
 
 class InternLM2ForRewardModel(InternLM2ForCausalLM):