OpenCL Token Generation Acceleration (#1459)

* Move back to C++ for OpenCL

* Refactor OpenCL code to work more like the CUDA code, add missing functions

* Deduplicate dequant kernels

* Add OpenCL compile options

* Use compile args for preprocessing constants

* Restore default platform + device selection by id behavior

---------

Co-authored-by: Johannes Gäßler <johannesg@5d6.de>
Co-authored-by: Henri Vasserman <henv@hot.ee>

1 files changed, 1 insertions, 0 deletions

diff --git a/ggml.h b/ggml.h
index 51a616c..c22d938 100644
--- a/ggml.h
+++ b/ggml.h
@@ -249,6 +249,7 @@ extern "C" {
     enum ggml_backend {
         GGML_BACKEND_CPU = 0,
         GGML_BACKEND_CUDA = 1,
+        GGML_BACKEND_CL = 2,
     };
 
     // model file types