[ModelOpt] Redesign the LinearMethod classes using the generic QuantKey-driven method (#49381)

Signed-off-by: Juhi Mittal <juhim@nvidia.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
This commit is contained in:
Juhi Mittal
2026-09-01 16:28:56 -04:00
committed by GitHub
co-authored by Claude Opus 4.8 mgoin
parent 4bf06be985
commit 7a977c0699
6 changed files with 1173 additions and 956 deletions
@@ -6,6 +6,8 @@ from dataclasses import dataclass
import torch
from vllm.model_executor.layers.quantization.utils.quant_utils import QuantKey
@dataclass
class Mxfp8LinearLayerConfig:
@@ -30,6 +32,12 @@ class Mxfp8LinearKernel(ABC):
assert self.is_supported()[0]
self.config = c
def input_quant_key(self) -> QuantKey | None:
"""Return the input quantization key supported by this kernel. If the kernel
does not support input quantization outside of the kernel, return None.
"""
return None
@classmethod
@abstractmethod
def is_supported(