[Quantization] Support online quantization with partially pre-quantized checkpoints (#51392)
Signed-off-by: Felix Marty <Felix.Marty@amd.com> Signed-off-by: mgoin <mgoin64@gmail.com> Co-authored-by: Codex <codex@openai.com> Co-authored-by: mgoin <mgoin64@gmail.com>
This commit is contained in:
co-authored by
Codex
mgoin
parent
a11dfcff89
commit
5690b02c03
@@ -12,6 +12,7 @@ if TYPE_CHECKING:
|
||||
)
|
||||
|
||||
from vllm.model_executor.layers.fused_moe import RoutedExperts
|
||||
from vllm.model_executor.layers.fused_moe.config import FusedMoEConfig
|
||||
from vllm.model_executor.layers.fused_moe.oracle.int8 import (
|
||||
convert_to_int8_moe_kernel_format,
|
||||
make_int8_moe_kernel,
|
||||
@@ -38,9 +39,9 @@ class Int8OnlineMoEMethod(OnlineMoEMethodBase):
|
||||
def __init__(
|
||||
self,
|
||||
*,
|
||||
layer: torch.nn.Module,
|
||||
moe: FusedMoEConfig,
|
||||
):
|
||||
super().__init__(layer.moe_config)
|
||||
super().__init__(moe)
|
||||
self.int8_backend, self.experts_cls = select_int8_moe_backend(
|
||||
config=self.moe,
|
||||
weight_key=kInt8StaticChannelSym,
|
||||
|
||||
Reference in New Issue
Block a user