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/gguf.py
View File

@@ -13,6 +13,7 @@ from vllm.model_executor.layers.activation import SiluAndMul
from vllm.model_executor.layers.fused_moe.layer import (FusedMoE,
FusedMoEMethodBase)
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, QuantizeMethodBase)
from vllm.model_executor.layers.vocab_parallel_embedding import (
@@ -31,7 +32,7 @@ class GGUFConfig(QuantizationConfig):
def __repr__(self) -> str:
return ("GGUFConfig()")
def get_name(self) -> str:
def get_name(self) -> QuantizationMethods:
return "gguf"
def get_supported_act_dtypes(self) -> List[torch.dtype]: