[Models] Add remaining model PP support (#7168)

Signed-off-by: Muralidhar Andoorveedu <muralidhar.andoorveedu@centml.ai>
Signed-off-by: Murali Andoorveedu <muralidhar.andoorveedu@centml.ai>
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
This commit is contained in:
Murali Andoorveedu
2024-10-04 10:56:58 +08:00
committed by GitHub
co-authored by DarkLight1337
parent 303d44790a
commit 0f6d7a9a34
69 changed files with 2585 additions and 1344 deletions
+7 -2
View File
@@ -29,11 +29,12 @@ import torch
from transformers import LlamaConfig
from vllm.config import CacheConfig, LoRAConfig
from vllm.model_executor.layers.quantization.base_config import (
QuantizationConfig)
from vllm.model_executor.layers.quantization import QuantizationConfig
from vllm.model_executor.model_loader.weight_utils import default_weight_loader
from vllm.model_executor.models.llama import LlamaForCausalLM
from .utils import is_pp_missing_parameter
class DeciLMForCausalLM(LlamaForCausalLM):
"""
@@ -91,6 +92,8 @@ class DeciLMForCausalLM(LlamaForCausalLM):
# 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)
@@ -99,6 +102,8 @@ class DeciLMForCausalLM(LlamaForCausalLM):
# 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)