biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

Remove ScaledActivation for AWQ (#10057)

Browse Source 
Signed-off-by: mgoin <michael@neuralmagic.com>
This commit is contained in:
Michael Goin
2024-11-06 09:27:06 -05:00
committed by GitHub
parent 406d4cc480
commit 399c798608
34 changed files with 19 additions and 124 deletions
Download Patch File Download Diff File Expand all files Collapse all files

37
vllm/model_executor/layers/activation.py
View File

@@ -9,7 +9,6 @@ import torch.nn.functional as F
from vllm.distributed import (divide, get_tensor_model_parallel_rank,
get_tensor_model_parallel_world_size)
from vllm.model_executor.custom_op import CustomOp
from vllm.model_executor.layers.quantization import QuantizationConfig
from vllm.model_executor.utils import set_weight_attrs
from vllm.utils import LazyDict
@@ -277,28 +276,14 @@ _ACTIVATION_REGISTRY = LazyDict({
})
def get_act_fn(
act_fn_name: str,
quant_config: Optional[QuantizationConfig] = None,
intermediate_size: Optional[int] = None,
input_is_parallel: bool = True,
params_dtype: Optional[torch.dtype] = None,
) -> nn.Module:
def get_act_fn(act_fn_name: str) -> nn.Module:
"""Get an activation function by name."""
act_fn_name = act_fn_name.lower()
if act_fn_name not in _ACTIVATION_REGISTRY:
raise ValueError(
f"Activation function {act_fn_name!r} is not supported.")
act_fn = _ACTIVATION_REGISTRY[act_fn_name]
if (quant_config is not None
and act_fn_name in quant_config.get_scaled_act_names()):
if intermediate_size is None:
raise ValueError("intermediate_size must be specified for scaled "
"activation functions.")
return ScaledActivation(act_fn, intermediate_size, input_is_parallel,
params_dtype)
return act_fn
return _ACTIVATION_REGISTRY[act_fn_name]
_ACTIVATION_AND_MUL_REGISTRY = LazyDict({
@@ -307,25 +292,11 @@ _ACTIVATION_AND_MUL_REGISTRY = LazyDict({
})
def get_act_and_mul_fn(
act_fn_name: str,
quant_config: Optional[QuantizationConfig] = None,
intermediate_size: Optional[int] = None,
input_is_parallel: bool = True,
params_dtype: Optional[torch.dtype] = None,
) -> nn.Module:
def get_act_and_mul_fn(act_fn_name: str) -> nn.Module:
"""Get an activation-and-mul (i.e. SiluAndMul) function by name."""
act_fn_name = act_fn_name.lower()
if act_fn_name not in _ACTIVATION_AND_MUL_REGISTRY:
raise ValueError(
f"Activation function {act_fn_name!r} is not supported.")
act_fn = _ACTIVATION_AND_MUL_REGISTRY[act_fn_name]
if (quant_config is not None
and act_fn_name in quant_config.get_scaled_act_names()):
if intermediate_size is None:
raise ValueError("intermediate_size must be specified for scaled "
"activation functions.")
return ScaledActivation(act_fn, intermediate_size, input_is_parallel,
params_dtype)
return act_fn
return _ACTIVATION_AND_MUL_REGISTRY[act_fn_name]