We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent a41492e commit 080ae7eCopy full SHA for 080ae7e
lightllm/server/router/model_infer/mode_backend/chunked_prefill/impl.py
@@ -46,6 +46,8 @@ def __init__(self) -> None:
46
else:
47
self.prefill = self.prefill_normal
48
self.decode = self.decode_normal
49
+
50
+ self.classed_req_strict_prefill = False
51
return
52
53
def infer_loop(self):
lightllm/server/router/model_infer/mode_backend/dp_backend/impl.py
@@ -58,6 +58,8 @@ def __init__(self) -> None:
58
self.decode = self.decode_overlap
59
60
61
62
63
64
65
0 commit comments