mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2026-04-23 00:17:25 +08:00
This reverts commit 96d2d4877b.
This commit is contained in:
@@ -90,7 +90,7 @@ class MockAttentionBackend:
|
||||
|
||||
|
||||
class MockQuantMethod:
|
||||
def apply(self, layer, x, gate, topk_ids_hookfunc=None):
|
||||
def apply(self, layer, x, gate):
|
||||
return x
|
||||
|
||||
|
||||
@@ -129,7 +129,6 @@ class TestChunkedMoE(unittest.TestCase):
|
||||
model_runner.speculative_decoding = False
|
||||
model_runner._init_share_inputs(mock_fd_config.scheduler_config.max_num_seqs)
|
||||
model_runner.share_inputs["caches"] = None
|
||||
model_runner.routing_replay_manager = None
|
||||
|
||||
if dist.get_rank() == 0:
|
||||
model_runner.share_inputs["ids_remove_padding"] = paddle.ones([10])
|
||||
@@ -149,7 +148,6 @@ class TestChunkedMoE(unittest.TestCase):
|
||||
|
||||
fused_moe.fd_config = mock_fd_config
|
||||
fused_moe.quant_method = MockQuantMethod()
|
||||
fused_moe.enable_routing_replay = None
|
||||
return fused_moe
|
||||
|
||||
def run_model_runner(self):
|
||||
|
||||
Reference in New Issue
Block a user