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

OpenCL Token Generation Acceleration (#1459)

Browse source 
* 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>
This commit is contained in:
0cc4m 2023-05-22 23:33:24 +02:00 • committed by GitHub
parent 7e4ea5beff
commit 2e6cd4b025
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
8 changed files with 1113 additions and 536 deletions
Download patch file Download diff file Expand all files Collapse all files

1
ggml.h
View file

@ -249,6 +249,7 @@ extern "C" {
enum ggml_backend {
GGML_BACKEND_CPU = 0,
GGML_BACKEND_CUDA = 1,
GGML_BACKEND_CL = 2,
};
// model file types