mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2026-04-23 00:17:25 +08:00
[Optimization] Support FA2/FA3/FA4 with attn_mask_q (#6354)
* support FA4 sm100 * flash attn backend support mask * flash attn backend run flashmask correct * add test for flash_attn_backend and flash_attn_func * check * add test for fa4 * requirements.txt add fa4 whl * check test on sm100 * fix CI conflict * add enable_torch_proxy for flash_mask * lazy import fa4 * check * fix tests import * check test_load_mpt import
This commit is contained in:
@@ -18,11 +18,11 @@ import unittest
|
||||
from unittest.mock import Mock, patch
|
||||
|
||||
import paddle
|
||||
from utils import FakeModelConfig, get_default_test_fd_config
|
||||
|
||||
from fastdeploy.config import SpeculativeConfig
|
||||
from fastdeploy.engine.request import Request, RequestType
|
||||
from fastdeploy.spec_decode.mtp import MTPProposer
|
||||
from tests.utils import FakeModelConfig, get_default_test_fd_config
|
||||
|
||||
|
||||
class TestMTPProposer(unittest.TestCase):
|
||||
|
||||
Reference in New Issue
Block a user