File size: 1,206 Bytes
e6066e8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
# Copyright (c) 2025 SandAI. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

import torch


def replace_fa_with_sage(gm: torch.fx.GraphModule) -> torch.fx.GraphModule:
    for node in gm.graph.nodes:
        if node.op == "call_function" and node.target == torch.ops.athena.flash_attn_func:
            node.target = torch.ops.athena.sage_attn_func


class FullGraphPassManager:
    """
    A manager to apply various graph passes on the full graph before splitting.
    """

    def __init__(self, pass_config):
        self.pass_config = pass_config

    def __call__(self, gm: torch.fx.GraphModule):
        if self.pass_config.enable_sage_attn:
            replace_fa_with_sage(gm)