[MOE Refactor] Remove QuantType in prepare_finalize.py (#6534)
### What this PR does / why we need it? To prevent confusion between different QuantType classes, we remove** QuantType in prepare_finalize.py - vLLM version: v0.15.0 - vLLM main: https://github.com/vllm-project/vllm/commit/v0.15.0 Signed-off-by: shenchuxiaofugui <1311027364@qq.com>
This commit is contained in:
@@ -15,7 +15,6 @@
|
||||
# This file is a part of the vllm-ascend project.
|
||||
|
||||
from abc import ABC, abstractmethod
|
||||
from enum import Enum
|
||||
|
||||
import torch
|
||||
import torch.distributed as dist
|
||||
@@ -32,15 +31,10 @@ from vllm.model_executor.layers.fused_moe import FusedMoEConfig
|
||||
|
||||
from vllm_ascend.ascend_config import get_ascend_config
|
||||
from vllm_ascend.distributed.utils import fc3_all_gather_and_maybe_unpad_impl
|
||||
from vllm_ascend.quantization.methods.base import QuantType
|
||||
from vllm_ascend.utils import enable_sp, npu_stream_switch, prefill_context_parallel_enable
|
||||
|
||||
|
||||
class QuantType(Enum):
|
||||
NONE = 0
|
||||
W8A8 = 1
|
||||
W4A8 = 2
|
||||
|
||||
|
||||
class PrepareAndFinalize(ABC):
|
||||
"""
|
||||
Abstract base class for MoE (Mixture-of-Experts) tensor preparation and finalization
|
||||
|
||||
Reference in New Issue
Block a user