apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2026-04-24 01:29:57 +08:00
Code Issues Actions 9 Packages Projects Releases Wiki Activity

[Other] Adjust GPUModelRunner to enhance compatibility (#6851)

Browse Source
This commit is contained in:
ming1753
2026-03-16 14:49:19 +08:00
committed by GitHub
parent 04fde3b227
commit bb925c605f
25 changed files with 224 additions and 248 deletions
Download Patch File Download Diff File Expand all files Collapse all files
fastdeploy/model_executor/layers/attention/append_attn_backend.py
-1
View File
@@ -326,7 +326,6 @@ class AppendAttentionBackend(AttentionBackend):
cache_v_scales = getattr(layer, "cache_v_scale", None)
if layer.layer_id == 0:
# print(forward_meta.seq_lens_this_time)
get_block_shape_and_split_kv_block(
forward_meta.seq_lens_encoder,
forward_meta.seq_lens_decoder,