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

Improve configs - ModelConfig (#17130)

Browse Source 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
Harry Mellor
2025-04-30 03:38:22 +01:00
committed by GitHub
parent 2c4f59afc3
commit 13698db634
36 changed files with 490 additions and 648 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
vllm/model_executor/layers/quantization/torchao.py
View File

@@ -6,6 +6,7 @@ import torch.nn.functional as F
from torch.nn.parameter import Parameter
from vllm.model_executor.layers.linear import LinearBase, LinearMethodBase
from vllm.model_executor.layers.quantization import QuantizationMethods
from vllm.model_executor.layers.quantization.base_config import (
QuantizationConfig)
from vllm.model_executor.utils import set_weight_attrs
@@ -20,7 +21,7 @@ class TorchAOConfig(QuantizationConfig):
def __repr__(self) -> str:
return f"TorchAOConfig({self.torchao_config})"
def get_name(self) -> str:
def get_name(self) -> QuantizationMethods:
return "torchao"
def get_supported_act_dtypes(self) -> List[torch.dtype]: