ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-04-28 02:11:50 +00:00
Code Issues Packages Projects Releases Wiki Activity

RPC: support multiple devices including cpu (#1024)

Browse Source 
* RPC support multiple devices

* rpc : update documentation (#16441)

Update the README file to match the newly added functionality of
exposing multiple devices from a single server.

Co-authored-by: Diego Devesa <slarengh@gmail.com>

# Conflicts:
#	examples/rpc/README.md

* Remove memory settings

* rpc : cache and reuse compute graphs (#15405)

Store the last computed graph and reuse it when possible.
Also do not return response from GRAPH_COMPUTE and assume it always
completes successfully. If this this is not the case, the server closes
the connection. This saves us a network round trip to the server.

* Add -cpu to include cpu backend

---------

Co-authored-by: firecoperana <firecoperana>
Co-authored-by: Radoslav Gerganov <rgerganov@gmail.com>
This commit is contained in:
firecoperana
2025-11-30 11:48:02 -06:00
committed by GitHub
parent 52adcf1e90
commit e89064e657
8 changed files with 734 additions and 381 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
ggml/include/ggml-rpc.h
View File

@@ -7,22 +7,22 @@
extern "C" {
#endif
#define RPC_PROTO_MAJOR_VERSION 2
#define RPC_PROTO_MINOR_VERSION 0
#define RPC_PROTO_MAJOR_VERSION 3
#define RPC_PROTO_MINOR_VERSION 5
#define RPC_PROTO_PATCH_VERSION 1
#define GGML_RPC_MAX_SERVERS 16
// backend API
GGML_API GGML_CALL ggml_backend_t ggml_backend_rpc_init(const char * endpoint);
GGML_API GGML_CALL ggml_backend_t ggml_backend_rpc_init(const char * endpoint, uint32_t device);
GGML_API GGML_CALL bool ggml_backend_is_rpc(ggml_backend_t backend);
GGML_API GGML_CALL ggml_backend_buffer_type_t ggml_backend_rpc_buffer_type(const char * endpoint);
GGML_API GGML_CALL ggml_backend_buffer_type_t ggml_backend_rpc_buffer_type(const char * endpoint, uint32_t device);
GGML_API GGML_CALL void ggml_backend_rpc_get_device_memory(const char * endpoint, size_t * free, size_t * total);
GGML_API GGML_CALL uint32_t ggml_backend_rpc_get_device_count(const char* endpoint);
GGML_API GGML_CALL void ggml_backend_rpc_start_server(ggml_backend_t backend, const char * endpoint,
const char * cache_dir,
size_t free_mem, size_t total_mem);
GGML_API GGML_CALL void ggml_backend_rpc_get_device_memory(const char * endpoint, uint32_t device, size_t * free, size_t * total);
GGML_API GGML_CALL void ggml_backend_rpc_start_server(const char * endpoint, const char* cache_dir, size_t device, ggml_backend_t * devices, size_t* free_mem, size_t* total_mem);
#ifdef __cplusplus
}