diff options
| author | UEXTM.com <84163508+uextm@users.noreply.github.com> | 2024-02-24 11:27:36 -0500 |
|---|---|---|
| committer | Georgi Gerganov <ggerganov@gmail.com> | 2024-02-28 11:17:05 +0200 |
| commit | 5f706718566e3a5147916dc381f3b99de0ffad47 (patch) | |
| tree | a8375d9ea4eae5abac38cc0aba29fdedbf4fe9f5 /ggml-cuda.cu | |
| parent | a693bea1e6762a17b78b6ddf4611e54136941ea2 (diff) | |
Introduce backend GUIDs (ggml/743)
* 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>
Diffstat (limited to 'ggml-cuda.cu')
| -rw-r--r-- | ggml-cuda.cu | 8 |
1 files changed, 7 insertions, 1 deletions
diff --git a/ggml-cuda.cu b/ggml-cuda.cu index 831c84ef..0c6501e9 100644 --- a/ggml-cuda.cu +++ b/ggml-cuda.cu @@ -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() { |