apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-05 16:48:03 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

Clear dead code And supplementary notes (#2757)
Some checks failed
Deploy GitHub Pages / deploy (push) Has been cancelled
Details

Browse Source 
* 1.supplementary notes 2.delete dead code

* fix bug of forward meta

* Global modification of forward meta

* fix vl model_runner bug
This commit is contained in:
RAM
2025-07-09 16:17:34 +08:00
committed by GitHub
parent b89180f1cd
commit 03a74995b8
12 changed files with 248 additions and 463 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
test/layers/test_attention.py
View File

@@ -21,8 +21,7 @@ import paddle
from fastdeploy.model_executor.layers.attention import (
Attention, PaddleNativeAttnBackend)
from fastdeploy.worker.forward_meta import (ForwardMeta, ForwardMode,
MHATokenToKVPool)
from fastdeploy.worker.forward_meta import ForwardMeta, ForwardMode
class MockModelRunner:
@@ -63,15 +62,6 @@ class MockModelRunner:
},
)
self.page_size = page_size
max_total_num_tokens = max_batch_size * max_context_len
self.token_to_kv_pool = MHATokenToKVPool(
size=max_total_num_tokens,
page_size=page_size,
dtype=self.dtype,
head_num=num_heads,
head_dim=head_dim,
layer_num=1, # only consider layer=1 for unit test
device=self.device)
class TestNativePaddleAttentionBackend(unittest.TestCase):