[CPU] Support FP8 KV cache (#32733)
Co-authored-by: Zheng, Beilei <beilei.zheng@intel.com> Co-authored-by: mingfeima <mingfei.ma@intel.com>
This commit is contained in:
co-authored by
Zheng, Beilei
mingfeima
parent
e874ae64cd
commit
26f760d5c0
@@ -1114,6 +1114,8 @@ class TestExtendAttentionTreeMask(CustomTestCase):
|
||||
o_extend,
|
||||
k_buffer,
|
||||
v_buffer,
|
||||
1.0, # k_buf_scale
|
||||
1.0, # v_buf_scale
|
||||
req_to_token,
|
||||
req_pool_indices,
|
||||
seq_lens,
|
||||
|
||||
Reference in New Issue
Block a user