baalajimaestro/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

feat: Update llama.cpp

Browse source
This commit is contained in:
Andrei Betlen 2024-03-10 23:45:05 -04:00
parent a7281994d8
commit 08e910f7a7
2 changed files with 12 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

11
llama_cpp/llama_cpp.py
View file

@ -1728,6 +1728,17 @@ def llama_set_n_threads(
"""
...
# // Set whether to use causal attention or not
# // If set to true, the model will only attend to the past tokens
# LLAMA_API void llama_set_causal_attn(struct llama_context * ctx, bool causal_attn);
@ctypes_function("llama_set_causal_attn", [llama_context_p_ctypes, ctypes.c_bool], None)
def llama_set_causal_attn(ctx: llama_context_p, causal_attn: bool, /):
"""Set whether to use causal attention or not
If set to true, the model will only attend to the past tokens"""
...
# // Set abort callback
# LLAMA_API void llama_set_abort_callback(struct llama_context * ctx, ggml_abort_callback abort_callback, void * abort_callback_data);
@ctypes_function(

2
vendor/llama.cpp vendored

@ -1 +1 @@
Subproject commit c2101a2e909ac7c08976d414e64e96c90ee5fa9e
Subproject commit 3814a07392d2bdc22911652bc7c2f9bdb0ce042e