[NPU]TP Communications compression For Qwen3 models for NPU (#20520)
Co-authored-by: ronnie_zheng <zl19940307@163.com>
This commit is contained in:
co-authored by
ronnie_zheng
parent
ebbaab5597
commit
83bf5d6869
@@ -4,7 +4,7 @@ import time
|
||||
|
||||
import numpy as np
|
||||
|
||||
from sglang.api import set_default_backend
|
||||
from sglang.lang.api import set_default_backend
|
||||
from sglang.test.test_utils import (
|
||||
add_common_sglang_args_and_parse,
|
||||
select_sglang_backend,
|
||||
|
||||
Reference in New Issue
Block a user