mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2026-04-23 00:17:25 +08:00
[Feature] consider multimodal model when dummy run (#6045)
* add mm do profile * updata code * update code * update code * update code * update test case * update code * update code * fix xpu bug * update code * add mm do profile * update test case * update code
This commit is contained in:
@@ -56,6 +56,7 @@ class TestRedundantExpertManager(unittest.TestCase):
|
||||
model_cfg.moe_layer_start_index = 1
|
||||
model_cfg.model = "/test/model"
|
||||
model_cfg.architectures = ["test_model"]
|
||||
model_cfg.mm_max_tokens_per_item = None
|
||||
cache_cfg.bytes_per_layer_per_block = 1
|
||||
|
||||
parallel_cfg = ParallelConfig(args)
|
||||
|
||||
Reference in New Issue
Block a user