root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-11-14 23:09:53 +00:00
Code Issues Actions 14 Packages Projects Releases Wiki Activity

rpc : enable vulkan (#9714)
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
Details
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
Details
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
Details
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
Details
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
Details
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
Details
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
Details
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
Details
Nix CI / nix-eval (macos-latest) (push) Waiting to run
Details
Nix CI / nix-eval (ubuntu-latest) (push) Waiting to run
Details
Nix CI / nix-build (macos-latest) (push) Waiting to run
Details
Nix CI / nix-build (ubuntu-latest) (push) Waiting to run
Details
flake8 Lint / Lint (push) Waiting to run
Details

Browse Source 
closes #8536
This commit is contained in:
Radoslav Gerganov 2024-10-03 13:00:52 +03:00 committed by GitHub
parent 5639971466
commit 841713e1e4
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 12 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
examples/rpc/rpc-server.cpp
View File

@ -6,6 +6,10 @@
#include "ggml-metal.h" #include "ggml-metal.h"
#endif #endif
#ifdef GGML_USE_VULKAN
#include "ggml-vulkan.h"
#endif
#include "ggml-rpc.h" #include "ggml-rpc.h"
#ifdef _WIN32 #ifdef _WIN32
# include <windows.h> # include <windows.h>
@ -79,6 +83,12 @@ static ggml_backend_t create_backend() {
if (!backend) { if (!backend) {
fprintf(stderr, "%s: ggml_backend_metal_init() failed\n", __func__); fprintf(stderr, "%s: ggml_backend_metal_init() failed\n", __func__);
} }
#elif GGML_USE_VULKAN
fprintf(stderr, "%s: using Vulkan backend\n", __func__);
backend = ggml_backend_vk_init(0); // init device 0
if (!backend) {
fprintf(stderr, "%s: ggml_backend_vulkan_init() failed\n", __func__);
}
#endif #endif
// if there aren't GPU Backends fallback to CPU backend // if there aren't GPU Backends fallback to CPU backend
@ -92,6 +102,8 @@ static ggml_backend_t create_backend() {
static void get_backend_memory(size_t * free_mem, size_t * total_mem) { static void get_backend_memory(size_t * free_mem, size_t * total_mem) {
#ifdef GGML_USE_CUDA #ifdef GGML_USE_CUDA
ggml_backend_cuda_get_device_memory(0, free_mem, total_mem); ggml_backend_cuda_get_device_memory(0, free_mem, total_mem);
#elif GGML_USE_VULKAN
ggml_backend_vk_get_device_memory(0, free_mem, total_mem);
#else #else
#ifdef _WIN32 #ifdef _WIN32
MEMORYSTATUSEX status; MEMORYSTATUSEX status;