[Model] Use upstream GLM-5.3 and Qwen4-Exp configs and processor (#57387)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com> Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
This commit is contained in:
co-authored by
Claude Opus 5
parent
866f02db8a
commit
e3cae8d2ac
@@ -6,6 +6,7 @@ from collections.abc import Iterable
|
||||
|
||||
import torch
|
||||
from torch import nn
|
||||
from transformers import Qwen4ExpTextConfig
|
||||
|
||||
from vllm.config import get_current_vllm_config
|
||||
from vllm.logger import init_logger
|
||||
@@ -13,9 +14,6 @@ from vllm.model_executor.layers.quantization.base_config import (
|
||||
QuantizationConfig,
|
||||
)
|
||||
from vllm.model_executor.models.utils import AutoWeightsLoader
|
||||
from vllm.transformers_utils.configs.qwen4_exp import (
|
||||
Qwen4ExpTextConfig,
|
||||
)
|
||||
|
||||
from ..common.ngram_embedding import (
|
||||
Qwen4ExpPLEDeviceEmbedding,
|
||||
|
||||
Reference in New Issue
Block a user