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

Update llama.cpp

Browse source
This commit is contained in:
Andrei Betlen 2023-09-01 14:26:13 -04:00
parent 47de3ab104
commit 186626d58e
2 changed files with 3 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
llama_cpp/llama_cpp.py
View file

@ -294,6 +294,7 @@ llama_log_callback = ctypes.CFUNCTYPE(None, c_int, c_char_p, c_void_p)
# enum llama_ftype ftype; // quantize to this llama_ftype
# bool allow_requantize; // allow quantizing non-f32/f16 tensors
# bool quantize_output_tensor; // quantize output.weight
# bool only_copy; // only copy tensors - ftype, allow_requantize and quantize_output_tensor are ignored
# } llama_model_quantize_params;
class llama_model_quantize_params(Structure):
_fields_ = [
@ -301,6 +302,7 @@ class llama_model_quantize_params(Structure):
("ftype", c_int),
("allow_requantize", c_bool),
("quantize_output_tensor", c_bool),
("only_copy", c_bool),
]

2
vendor/llama.cpp vendored

@ -1 +1 @@
Subproject commit bcce96ba4dd95482824700c4ce2455fe8c49055a
Subproject commit 69fdbb9abc8907dd2a9ffdd840cba92d678a660a