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

Update llama.cpp (llama_mmap_supported)

Browse source
This commit is contained in:
Andrei Betlen 2023-04-09 22:01:33 -04:00 • committed by Don Mahurin
parent d0a7ce9abf
commit ce0ca60b56
1 changed files with 12 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

12
examples/llama_cpp.py
View file

@ -94,6 +94,7 @@ class llama_context_params(Structure):
c_bool, c_bool,
), # the llama_eval() call computes all logits, not just the last one ), # the llama_eval() call computes all logits, not just the last one
("vocab_only", c_bool), # only load the vocabulary, no weights ("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 ("use_mlock", c_bool), # force system to keep model in RAM
("embedding", c_bool), # embedding mode only ("embedding", c_bool), # embedding mode only
# called with a progress value between 0 and 1, pass NULL to disable # called with a progress value between 0 and 1, pass NULL to disable
@ -116,6 +117,17 @@ def llama_context_default_params() -> llama_context_params:
_lib.llama_context_default_params.argtypes = [] _lib.llama_context_default_params.argtypes = []
_lib.llama_context_default_params.restype = llama_context_params _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. # Various functions for loading a ggml llama model.
# Allocate (almost) all memory needed for the model. # Allocate (almost) all memory needed for the model.