mirror of
https://github.com/oobabooga/text-generation-webui.git
synced 2025-12-06 07:12:10 +01:00
llama.cpp: Always pass --flash-attn on
This commit is contained in:
parent
2395c647d4
commit
f3829b268a
|
|
@ -316,6 +316,7 @@ class LlamaServer:
|
|||
"--batch-size", str(shared.args.batch_size),
|
||||
"--port", str(self.port),
|
||||
"--no-webui",
|
||||
"--flash-attn", "on",
|
||||
]
|
||||
|
||||
if shared.args.threads > 0:
|
||||
|
|
|
|||
Loading…
Reference in a new issue