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
2023-05-03 09:33:30 -04:00
parent c2e31eecee
commit 1d47cce222
2 changed files with 4 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
llama_cpp/llama_cpp.py
View File

@@ -71,7 +71,7 @@ LLAMA_FILE_VERSION = ctypes.c_int(1)
LLAMA_FILE_MAGIC = b"ggjt"
LLAMA_FILE_MAGIC_UNVERSIONED = b"ggml"
LLAMA_SESSION_MAGIC = b"ggsn"
LLAMA_SESSION_VERSION = ctypes.c_int(0)
LLAMA_SESSION_VERSION = ctypes.c_int(1)
llama_context_p = c_void_p
@@ -239,7 +239,8 @@ _lib.llama_set_rng_seed.argtypes = [llama_context_p, c_int]
_lib.llama_set_rng_seed.restype = None
# Returns the size in bytes of the state (rng, logits, embedding and kv_cache)
# Returns the maximum size in bytes of the state (rng, logits, embedding
# and kv_cache) - will often be smaller after compacting tokens
def llama_get_state_size(ctx: llama_context_p) -> c_size_t:
return _lib.llama_get_state_size(ctx)