[Feature][Humming] Humming feature integration (#56685)
Signed-off-by: jinzhen.ljz <jinzhen.ljz@antgroup.com> Signed-off-by: mgoin <mgoin64@gmail.com> Co-authored-by: Codex <noreply@openai.com> Co-authored-by: mgoin <mgoin64@gmail.com>
This commit is contained in:
co-authored by
Codex
mgoin
parent
27757dde02
commit
7d99c2c4fd
@@ -4,7 +4,7 @@
|
||||
import torch
|
||||
|
||||
from vllm.logger import init_logger
|
||||
from vllm.model_executor.layers.quantization.utils.humming_utils import (
|
||||
from vllm.model_executor.layers.quantization.utils.humming import (
|
||||
apply_humming_linear,
|
||||
convert_linear_layer_to_humming_standard,
|
||||
get_humming_linear_compute_config,
|
||||
@@ -92,6 +92,7 @@ class HummingFP8ScaledMMLinearKernel(FP8ScaledMMLinearKernel):
|
||||
return apply_humming_linear(
|
||||
layer,
|
||||
x,
|
||||
skip_bias_add=bias is None,
|
||||
layer_config=self.layer_config,
|
||||
compute_config=self.compute_config,
|
||||
locks=self.locks,
|
||||
@@ -158,6 +159,7 @@ class HummingInt8ScaledMMLinearKernel(Int8ScaledMMLinearKernel):
|
||||
return apply_humming_linear(
|
||||
layer,
|
||||
x,
|
||||
skip_bias_add=bias is None,
|
||||
layer_config=self.layer_config,
|
||||
compute_config=self.compute_config,
|
||||
locks=self.locks,
|
||||
|
||||
Reference in New Issue
Block a user