apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2026-04-23 00:17:25 +08:00
Code Issues Actions 19 Packages Projects Releases Wiki Activity

[PD Disaggregation] pd + cache_storage support vl model (#6906)

Browse Source 
* pd + cache_storage support vl model

* support vl model

* fix test
This commit is contained in:
jc
2026-03-23 15:35:20 +08:00
committed by GitHub
parent 5416da8c6e
commit bb881c2c0a
3 changed files with 51 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/cache_manager/test_prefix_cache_manager.py
+6 -1
View File
@@ -1294,7 +1294,12 @@ class TestPrefixCacheManagerCoverage(unittest.TestCase):
manager = _create_manager(num_gpu_blocks=6)
manager.kvcache_storage_backend = "memory"
manager.prefix_tree_status_signal = SimpleNamespace(value=np.array([PrefixTreeStatus.NORMAL]))
task = SimpleNamespace(prompt_token_ids=[1, 2, 3, 4, 5, 6], output_token_ids=[], request_id="storage-req")
task = SimpleNamespace(
prompt_token_ids=[1, 2, 3, 4, 5, 6],
output_token_ids=[],
request_id="storage-req",
multimodal_inputs=None,
)
with (
patch.object(manager, "mm_match_block", return_value=([], [], [], manager.radix_tree_root, 0, 0)),