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 2024-05-24 01:43:36 -04:00
parent 5a595f035a
commit 087cc0b036
2 changed files with 17 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

16
llama_cpp/llama_cpp.py
View file

@ -2265,6 +2265,22 @@ def llama_set_n_threads(
...
# // Get the number of threads used for generation of a single token.
# LLAMA_API uint32_t llama_n_threads(struct llama_context * ctx);
@ctypes_function("llama_n_threads", [llama_context_p_ctypes], ctypes.c_uint32)
def llama_n_threads(ctx: llama_context_p, /) -> int:
"""Get the number of threads used for generation of a single token"""
...
# // Get the number of threads used for prompt and batch processing (multiple token).
# LLAMA_API uint32_t llama_n_threads_batch(struct llama_context * ctx);
@ctypes_function("llama_n_threads_batch", [llama_context_p_ctypes], ctypes.c_uint32)
def llama_n_threads_batch(ctx: llama_context_p, /) -> int:
"""Get the number of threads used for prompt and batch processing (multiple token)"""
...
# // 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);

2
vendor/llama.cpp vendored

@ -1 +1 @@
Subproject commit 201cc11afa0a1950e1f632390b2ac6c937a0d8f0
Subproject commit 0df0aa8e43c3378975269a51f9b876c8692e70da