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 2023-07-24 13:08:06 -04:00
parent 985d559971
commit d8a3ddbb1c
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

@ -163,6 +163,7 @@ llama_progress_callback = ctypes.CFUNCTYPE(None, c_float, c_void_p)
# int32_t n_ctx; // text context
# int32_t n_batch; // prompt processing batch size
# int32_t n_gqa; // grouped-query attention (TEMP - will be moved to model hparams)
# float rms_norm_eps; // rms norm epsilon (TEMP - will be moved to model hparams)
# int32_t n_gpu_layers; // number of layers to store in VRAM
# int32_t main_gpu; // the GPU that is used for scratch and small tensors
#
@ -193,6 +194,7 @@ class llama_context_params(Structure):
("n_ctx", c_int32),
("n_batch", c_int32),
("n_gqa", c_int32),
("rms_norm_eps", c_float),
("n_gpu_layers", c_int32),
("main_gpu", c_int32),
("tensor_split", POINTER(c_float)),

2
vendor/llama.cpp vendored

@ -1 +1 @@
Subproject commit 84e09a7d8bc4ab6d658b5cd81295ac0add60be78
Subproject commit 41c674161fb2459bdf7806d1eebead15bc5d046e