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

Introduce backend GUIDs (ggml/743)

Browse source 
* Introduce backend GUIDs

Initial proposed implementation of backend GUIDs
(Discussed in https://github.com/ggerganov/ggml/pull/741)

Hardcoded CPU backend GUID (for now)
Change ggml_backend_is_cpu logic to use GUID

* Remove redundant functions

Remove redundant functions `ggml_backend_i::get_name` and `ggml_backend_guid` which are not desired for future expansion

* Add spaces to match style

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

* Fix brace style to match

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

* Add void to () in function signature

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

* Add back ggml_backend_guid and make CPU_GUID a local static in ggml_backend_cpu_guid

* add guids to all backends

ggml-ci

---------

Co-authored-by: slaren <slarengh@gmail.com>
This commit is contained in:
UEXTM.com 2024-02-24 11:27:36 -05:00 • committed by Georgi Gerganov
parent a693bea1e6
commit 5f70671856
No known key found for this signature in database
GPG key ID: BF970631944C16B7
10 changed files with 66 additions and 8 deletions
Download patch file Download diff file Expand all files Collapse all files

8
ggml-cuda.cu
View file

@ -12277,6 +12277,11 @@ static ggml_backend_i ggml_backend_cuda_interface = {
/* .supports_op = */ ggml_backend_cuda_supports_op,
};
static ggml_guid_t ggml_backend_cuda_guid() {
static ggml_guid guid = { 0x2c, 0xdd, 0xe8, 0x1c, 0x65, 0xb3, 0x65, 0x73, 0x6a, 0x12, 0x88, 0x61, 0x1c, 0xc9, 0xdc, 0x25 };
return &guid;
}
GGML_CALL ggml_backend_t ggml_backend_cuda_init(int device) {
ggml_init_cublas(); // TODO: remove from ggml.c
@ -12294,6 +12299,7 @@ GGML_CALL ggml_backend_t ggml_backend_cuda_init(int device) {
};
ggml_backend_t cuda_backend = new ggml_backend {
/* .guid = */ ggml_backend_cuda_guid(),
/* .interface = */ ggml_backend_cuda_interface,
/* .context = */ ctx
};
@ -12302,7 +12308,7 @@ GGML_CALL ggml_backend_t ggml_backend_cuda_init(int device) {
}
GGML_CALL bool ggml_backend_is_cuda(ggml_backend_t backend) {
return backend && backend->iface.get_name == ggml_backend_cuda_name;
return backend != NULL && ggml_guid_matches(backend->guid, ggml_backend_cuda_guid());
}
GGML_CALL int ggml_backend_cuda_get_device_count() {