7a977c0699
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>
65 lines
1.7 KiB
Python
65 lines
1.7 KiB
Python
# SPDX-License-Identifier: Apache-2.0
|
|
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
|
|
|
from abc import ABC, abstractmethod
|
|
from dataclasses import dataclass
|
|
|
|
import torch
|
|
|
|
from vllm.model_executor.layers.quantization.utils.quant_utils import QuantKey
|
|
|
|
|
|
@dataclass
|
|
class Mxfp8LinearLayerConfig:
|
|
"""Configuration for an MXFP8 linear layer.
|
|
|
|
All MXFP8 layers share the same structure: FP8-E4M3 weights with
|
|
uint8 (E8M0) per-block scales at block size 32.
|
|
"""
|
|
|
|
pass
|
|
|
|
|
|
class Mxfp8LinearKernel(ABC):
|
|
"""Base class for MXFP8 quantized linear kernels.
|
|
|
|
Each subclass implements a specific GEMM backend (FlashInfer CUTLASS,
|
|
Marlin, emulation).
|
|
"""
|
|
|
|
def __init__(self, c: Mxfp8LinearLayerConfig) -> None:
|
|
assert self.can_implement(c)[0]
|
|
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(
|
|
cls, compute_capability: int | None = None
|
|
) -> tuple[bool, str | None]:
|
|
raise NotImplementedError
|
|
|
|
@classmethod
|
|
@abstractmethod
|
|
def can_implement(cls, c: Mxfp8LinearLayerConfig) -> tuple[bool, str | None]:
|
|
raise NotImplementedError
|
|
|
|
@abstractmethod
|
|
def process_weights_after_loading(self, layer: torch.nn.Module) -> None:
|
|
raise NotImplementedError
|
|
|
|
@abstractmethod
|
|
def apply_weights(
|
|
self,
|
|
layer: torch.nn.Module,
|
|
x: torch.Tensor,
|
|
bias: torch.Tensor | None = None,
|
|
) -> torch.Tensor:
|
|
raise NotImplementedError
|