alihan/llama-cpp-python
1
0
Fork 0
mirror of https://github.com/abetlen/llama-cpp-python.git synced 2023-09-07 17:34:22 +03:00
Code Issues Packages Projects Releases Wiki Activity

Update llama.cpp

Browse Source
This commit is contained in:
Andrei Betlen
2023-04-09 22:01:33 -04:00
parent e636214b4e
commit c3c2623e8b
2 changed files with 13 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
llama_cpp/llama_cpp.py
View File

@@ -77,6 +77,7 @@ class llama_context_params(Structure):
c_bool,
), # the llama_eval() call computes all logits, not just the last one
("vocab_only", c_bool), # only load the vocabulary, no weights
("use_mmap", c_bool), # use mmap if possible
("use_mlock", c_bool), # force system to keep model in RAM
("embedding", c_bool), # embedding mode only
# called with a progress value between 0 and 1, pass NULL to disable
@@ -99,6 +100,17 @@ def llama_context_default_params() -> llama_context_params:
_lib.llama_context_default_params.argtypes = []
_lib.llama_context_default_params.restype = llama_context_params
def llama_mmap_supported() -> c_bool:
return _lib.llama_mmap_supported()
_lib.llama_mmap_supported.argtypes = []
_lib.llama_mmap_supported.restype = c_bool
def llama_mlock_supported() -> c_bool:
return _lib.llama_mlock_supported()
_lib.llama_mlock_supported.argtypes = []
_lib.llama_mlock_supported.restype = c_bool
# Various functions for loading a ggml llama model.
# Allocate (almost) all memory needed for the model.