Improve configs - ModelConfig (#17130)

Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
Harry Mellor
2025-04-30 10:38:22 +08:00
committed by GitHub
parent 2c4f59afc3
commit 13698db634
36 changed files with 490 additions and 648 deletions
@@ -9,6 +9,7 @@ from torch.nn.parameter import Parameter
from vllm.logger import init_logger
from vllm.model_executor.layers.linear import (LinearBase, LinearMethodBase,
UnquantizedLinearMethod)
from vllm.model_executor.layers.quantization import QuantizationMethods
from vllm.model_executor.layers.quantization.base_config import (
QuantizationConfig, QuantizeMethodBase)
from vllm.model_executor.layers.quantization.utils.marlin_utils_fp8 import (
@@ -38,7 +39,7 @@ class FBGEMMFp8Config(QuantizationConfig):
self.fp8_linear = Fp8LinearOp()
@classmethod
def get_name(cls) -> str:
def get_name(cls) -> QuantizationMethods:
return "fbgemm_fp8"
@classmethod