root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-11-13 14:29:52 +00:00
Code Issues Actions 11 Packages Projects Releases Wiki Activity

mtgpu: enable VMM (#9597)
Some checks failed
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
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/full-cuda.Dockerfile platforms:linux/amd64 tag:full-cuda]) (push) Has been cancelled
Details
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/full.Dockerfile platforms:linux/amd64,linux/arm64 tag:full]) (push) Has been cancelled
Details
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-cli-cuda.Dockerfile platforms:linux/amd64 tag:light-cuda]) (push) Has been cancelled
Details
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-cli-intel.Dockerfile platforms:linux/amd64 tag:light-intel]) (push) Has been cancelled
Details
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-cli.Dockerfile platforms:linux/amd64,linux/arm64 tag:light]) (push) Has been cancelled
Details
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-server-cuda.Dockerfile platforms:linux/amd64 tag:server-cuda]) (push) Has been cancelled
Details
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-server-intel.Dockerfile platforms:linux/amd64 tag:server-intel]) (push) Has been cancelled
Details
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-server.Dockerfile platforms:linux/amd64,linux/arm64 tag:server]) (push) Has been cancelled
Details

Browse Source 
Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com>
This commit is contained in:
R0CKSTAR 2024-09-26 09:27:40 +08:00 committed by GitHub
parent ea9c32be71
commit 7691654c68
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 6 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
ggml/src/ggml-cuda.cu
View File

@ -187,7 +187,7 @@ static ggml_cuda_device_info ggml_cuda_init() {
for (int id = 0; id < info.device_count; ++id) {
int device_vmm = 0;
#if !defined(GGML_USE_HIPBLAS) && !defined(GGML_CUDA_NO_VMM) && !defined(GGML_USE_MUSA)
#if !defined(GGML_USE_HIPBLAS) && !defined(GGML_CUDA_NO_VMM)
CUdevice device;
CU_CHECK(cuDeviceGet(&device, id));
CU_CHECK(cuDeviceGetAttribute(&device_vmm, CU_DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED, device));
@ -199,7 +199,7 @@ static ggml_cuda_device_info ggml_cuda_init() {
alloc_prop.location.id = id;
CU_CHECK(cuMemGetAllocationGranularity(&info.devices[id].vmm_granularity, &alloc_prop, CU_MEM_ALLOC_GRANULARITY_RECOMMENDED));
}
#endif // !defined(GGML_USE_HIPBLAS) && !defined(GGML_CUDA_NO_VMM) && !defined(GGML_USE_MUSA)
#endif // !defined(GGML_USE_HIPBLAS) && !defined(GGML_CUDA_NO_VMM)
info.devices[id].vmm = !!device_vmm;
cudaDeviceProp prop;
@ -335,7 +335,7 @@ struct ggml_cuda_pool_leg : public ggml_cuda_pool {
};
// pool with virtual memory
#if !defined(GGML_USE_HIPBLAS) && !defined(GGML_CUDA_NO_VMM) && !defined(GGML_USE_MUSA)
#if !defined(GGML_USE_HIPBLAS) && !defined(GGML_CUDA_NO_VMM)
struct ggml_cuda_pool_vmm : public ggml_cuda_pool {
static const size_t CUDA_POOL_VMM_MAX_SIZE = 1ull << 35; // 32 GB
@ -429,14 +429,14 @@ struct ggml_cuda_pool_vmm : public ggml_cuda_pool {
GGML_ASSERT(ptr == (void *) (pool_addr + pool_used));
}
};
#endif // !defined(GGML_USE_HIPBLAS) && !defined(GGML_CUDA_NO_VMM) && !defined(GGML_USE_MUSA)
#endif // !defined(GGML_USE_HIPBLAS) && !defined(GGML_CUDA_NO_VMM)
std::unique_ptr<ggml_cuda_pool> ggml_backend_cuda_context::new_pool_for_device(int device) {
#if !defined(GGML_USE_HIPBLAS) && !defined(GGML_CUDA_NO_VMM) && !defined(GGML_USE_MUSA)
#if !defined(GGML_USE_HIPBLAS) && !defined(GGML_CUDA_NO_VMM)
if (ggml_cuda_info().devices[device].vmm) {
return std::unique_ptr<ggml_cuda_pool>(new ggml_cuda_pool_vmm(device));
}
#endif // !defined(GGML_USE_HIPBLAS) && !defined(GGML_CUDA_NO_VMM) && !defined(GGML_USE_MUSA)
#endif // !defined(GGML_USE_HIPBLAS) && !defined(GGML_CUDA_NO_VMM)
return std::unique_ptr<ggml_cuda_pool>(new ggml_cuda_pool_leg(device));
}