[5/N] pass the whole config to model (#9983)
Signed-off-by: youkaichao <youkaichao@gmail.com>
This commit is contained in:
@@ -6,7 +6,7 @@ from torch import nn
|
||||
from transformers.configuration_utils import PretrainedConfig
|
||||
|
||||
from vllm.attention import Attention, AttentionMetadata
|
||||
from vllm.config import CacheConfig, LoRAConfig
|
||||
from vllm.config import CacheConfig, VllmConfig
|
||||
from vllm.distributed import (get_pp_group, get_tensor_model_parallel_rank,
|
||||
get_tensor_model_parallel_world_size)
|
||||
from vllm.model_executor.layers.linear import (MergedColumnParallelLinear,
|
||||
@@ -365,12 +365,13 @@ class Phi3SmallForCausalLM(nn.Module, SupportsPP):
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
config: PretrainedConfig,
|
||||
cache_config: Optional[CacheConfig] = None,
|
||||
quant_config: Optional[QuantizationConfig] = None,
|
||||
lora_config: Optional[LoRAConfig] = None,
|
||||
):
|
||||
vllm_config: VllmConfig,
|
||||
prefix: str = "",
|
||||
) -> None:
|
||||
super().__init__()
|
||||
config = vllm_config.model_config.hf_config
|
||||
cache_config = vllm_config.cache_config
|
||||
quant_config = vllm_config.quant_config
|
||||
self.config = config
|
||||
self.quant_config = quant_config
|
||||
self.model = Phi3SmallModel(config, cache_config, quant_config)
|
||||
|
||||
Reference in New Issue
Block a user