mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2024-11-14 23:09:53 +00:00
c83ad6d01e
Some checks are pending
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/full-cuda.Dockerfile platforms:linux/amd64 tag:full-cuda]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/full.Dockerfile platforms:linux/amd64,linux/arm64 tag:full]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-cli-cuda.Dockerfile platforms:linux/amd64 tag:light-cuda]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-cli-intel.Dockerfile platforms:linux/amd64 tag:light-intel]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-cli.Dockerfile platforms:linux/amd64,linux/arm64 tag:light]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-server-cuda.Dockerfile platforms:linux/amd64 tag:server-cuda]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-server-intel.Dockerfile platforms:linux/amd64 tag:server-intel]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-server.Dockerfile platforms:linux/amd64,linux/arm64 tag:server]) (push) Waiting to run
Nix CI / nix-eval (macos-latest) (push) Waiting to run
Nix CI / nix-eval (ubuntu-latest) (push) Waiting to run
Nix CI / nix-build (macos-latest) (push) Waiting to run
Nix CI / nix-build (ubuntu-latest) (push) Waiting to run
flake8 Lint / Lint (push) Waiting to run
Co-authored-by: Johannes Gäßler <johannesg@5d6.de>
25 lines
623 B
C
25 lines
623 B
C
#pragma once
|
|
|
|
#include "ggml.h"
|
|
#include "ggml-backend.h"
|
|
|
|
#ifdef __cplusplus
|
|
extern "C" {
|
|
#endif
|
|
|
|
#define GGML_RPC_MAX_SERVERS 16
|
|
|
|
// backend API
|
|
GGML_API ggml_backend_t ggml_backend_rpc_init(const char * endpoint);
|
|
GGML_API bool ggml_backend_is_rpc(ggml_backend_t backend);
|
|
|
|
GGML_API ggml_backend_buffer_type_t ggml_backend_rpc_buffer_type(const char * endpoint);
|
|
|
|
GGML_API void ggml_backend_rpc_get_device_memory(const char * endpoint, size_t * free, size_t * total);
|
|
|
|
GGML_API void start_rpc_server(ggml_backend_t backend, const char * endpoint, size_t free_mem, size_t total_mem);
|
|
|
|
#ifdef __cplusplus
|
|
}
|
|
#endif
|