mirror of
https://github.com/oobabooga/text-generation-webui.git
synced 2026-04-04 14:17:28 +00:00
Bump llama-cpp-python to 0.2.69, add --flash-attn option
This commit is contained in:
parent
0476f9fe70
commit
e61055253c
15 changed files with 66 additions and 58 deletions
|
|
@ -104,6 +104,7 @@ def list_model_elements():
|
|||
'no_offload_kqv',
|
||||
'row_split',
|
||||
'tensorcores',
|
||||
'flash-attn',
|
||||
'streaming_llm',
|
||||
'attention_sink_size',
|
||||
'hqq_backend',
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue