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

rpc : add backend registry / device interfaces (#9812)

Browse source 
* rpc : add backend registry / device interfaces

* llama : add llama_supports_rpc API

* ggml_backend_rpc_start_rpc_server -> ggml_backend_rpc_start_server
This commit is contained in:
Diego Devesa 2024-10-10 20:14:55 +02:00 • committed by GitHub
parent cf8e0a3bb9
commit 0e9f760eb1
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
8 changed files with 247 additions and 88 deletions
Download patch file Download diff file Expand all files Collapse all files

1
include/llama.h
View file

@ -433,6 +433,7 @@ extern "C" {
LLAMA_API bool llama_supports_mmap (void);
LLAMA_API bool llama_supports_mlock (void);
LLAMA_API bool llama_supports_gpu_offload(void);
LLAMA_API bool llama_supports_rpc (void);
LLAMA_API uint32_t llama_n_ctx (const struct llama_context * ctx);
LLAMA_API uint32_t llama_n_batch (const struct llama_context * ctx);