Remove unused kwargs from model definitions (#13555)
This commit is contained in:
@@ -23,13 +23,13 @@
|
||||
# limitations under the License.
|
||||
"""Inference-only Solar model compatible with HuggingFace weights."""
|
||||
|
||||
from typing import Any, Dict, Iterable, List, Optional, Set, Tuple, Union
|
||||
from typing import Any, Dict, Iterable, Optional, Set, Tuple, Union
|
||||
|
||||
import torch
|
||||
from torch import nn
|
||||
from transformers import PretrainedConfig
|
||||
|
||||
from vllm.attention import Attention, AttentionMetadata
|
||||
from vllm.attention import Attention
|
||||
from vllm.compilation.decorators import support_torch_compile
|
||||
from vllm.config import CacheConfig, VllmConfig
|
||||
from vllm.distributed import get_pp_group, get_tensor_model_parallel_world_size
|
||||
@@ -172,13 +172,11 @@ class SolarAttention(nn.Module):
|
||||
self,
|
||||
positions: torch.Tensor,
|
||||
hidden_states: torch.Tensor,
|
||||
kv_cache: torch.Tensor,
|
||||
attn_metadata: AttentionMetadata,
|
||||
) -> 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, k = self.rotary_emb(positions, q, k)
|
||||
attn_output = self.attn(q, k, v, kv_cache, attn_metadata)
|
||||
attn_output = self.attn(q, k, v)
|
||||
output, _ = self.o_proj(attn_output)
|
||||
return output
|
||||
|
||||
@@ -238,8 +236,6 @@ class SolarDecoderLayer(nn.Module):
|
||||
self,
|
||||
positions: torch.Tensor,
|
||||
hidden_states: torch.Tensor,
|
||||
kv_cache: torch.Tensor,
|
||||
attn_metadata: AttentionMetadata,
|
||||
residual: Optional[torch.Tensor],
|
||||
) -> Tuple[torch.Tensor, torch.Tensor]:
|
||||
# Self Attention
|
||||
@@ -252,8 +248,6 @@ class SolarDecoderLayer(nn.Module):
|
||||
hidden_states = self.self_attn(
|
||||
positions=positions,
|
||||
hidden_states=hidden_states,
|
||||
kv_cache=kv_cache,
|
||||
attn_metadata=attn_metadata,
|
||||
)
|
||||
|
||||
# Fully Connected
|
||||
@@ -315,8 +309,6 @@ class SolarModel(nn.Module):
|
||||
self,
|
||||
input_ids: Optional[torch.Tensor],
|
||||
positions: torch.Tensor,
|
||||
kv_caches: List[torch.Tensor],
|
||||
attn_metadata: AttentionMetadata,
|
||||
intermediate_tensors: Optional[IntermediateTensors],
|
||||
inputs_embeds: Optional[torch.Tensor] = None,
|
||||
) -> Union[torch.Tensor, IntermediateTensors]:
|
||||
@@ -357,8 +349,6 @@ class SolarModel(nn.Module):
|
||||
hidden_states, residual = layer(
|
||||
positions,
|
||||
hidden_states,
|
||||
kv_caches[i - self.start_layer],
|
||||
attn_metadata,
|
||||
residual,
|
||||
)
|
||||
|
||||
@@ -438,13 +428,10 @@ class SolarForCausalLM(nn.Module, SupportsLoRA, SupportsPP):
|
||||
self,
|
||||
input_ids: torch.Tensor,
|
||||
positions: torch.Tensor,
|
||||
kv_caches: List[torch.Tensor],
|
||||
attn_metadata: AttentionMetadata,
|
||||
intermediate_tensors: Optional[IntermediateTensors] = None,
|
||||
inputs_embeds: Optional[torch.Tensor] = None,
|
||||
) -> Union[torch.Tensor, IntermediateTensors]:
|
||||
model_output = self.model(input_ids, positions, kv_caches,
|
||||
attn_metadata, intermediate_tensors,
|
||||
model_output = self.model(input_ids, positions, intermediate_tensors,
|
||||
inputs_embeds)
|
||||
return model_output
|
||||
|
||||
|
||||
Reference in New Issue
Block a user