Update llama.cpp

abetlen · abetlen · commit 50f5c74ecf0f · 2024-05-14T09:30:04.000-04:00
diff --git a/llama_cpp/llama_cpp.py b/llama_cpp/llama_cpp.py
@@ -648,6 +648,9 @@ class llama_model_kv_override(ctypes.Structure):
 #     // proportion of the model (layers or rows) to offload to each GPU, size: llama_max_devices()
 #     const float * tensor_split;
 
+#     // comma separated list of RPC servers to use for offloading
+#     const char * rpc_servers;
+
 #     // Called with a progress value between 0.0 and 1.0. Pass NULL to disable.
 #     // If the provided progress_callback returns true, model loading continues.
 #     // If it returns false, model loading is immediately aborted.
@@ -674,6 +677,7 @@ class llama_model_params(ctypes.Structure):
         split_mode (int): how to split the model across multiple GPUs
         main_gpu (int): the GPU that is used for the entire model. main_gpu interpretation depends on split_mode: LLAMA_SPLIT_NONE: the GPU that is used for the entire model LLAMA_SPLIT_ROW: the GPU that is used for small tensors and intermediate results LLAMA_SPLIT_LAYER: ignored
         tensor_split (ctypes.Array[ctypes.ctypes.c_float]): proportion of the model (layers or rows) to offload to each GPU, size: llama_max_devices()
+        rpc_servers (ctypes.c_char_p): comma separated list of RPC servers to use for offloading
         progress_callback (llama_progress_callback): called with a progress value between 0.0 and 1.0. Pass NULL to disable. If the provided progress_callback returns true, model loading continues. If it returns false, model loading is immediately aborted.
         progress_callback_user_data (ctypes.ctypes.c_void_p): context pointer passed to the progress callback
         kv_overrides (ctypes.Array[llama_model_kv_override]): override key-value pairs of the model meta data
@@ -687,6 +691,7 @@ class llama_model_params(ctypes.Structure):
         split_mode: int
         main_gpu: int
         tensor_split: CtypesArray[ctypes.c_float]
+        rpc_servers: ctypes.c_char_p
         progress_callback: Callable[[float, ctypes.c_void_p], bool]
         progress_callback_user_data: ctypes.c_void_p
         kv_overrides: CtypesArray[llama_model_kv_override]
@@ -700,6 +705,7 @@ class llama_model_params(ctypes.Structure):
         ("split_mode", ctypes.c_int),
         ("main_gpu", ctypes.c_int32),
         ("tensor_split", ctypes.POINTER(ctypes.c_float)),
+        ("rpc_servers", ctypes.c_char_p),
         ("progress_callback", llama_progress_callback),
         ("progress_callback_user_data", ctypes.c_void_p),
         ("kv_overrides", ctypes.POINTER(llama_model_kv_override)),
diff --git a/vendor/llama.cpp b/vendor/llama.cpp
@@ -1 +1 @@
-Subproject commit 1c570d8beeebad95872dc738ea542a4a0022f78a
+Subproject commit 1265c670fd8e41e1947352c96c5179adda97fb2c
