EngineX-Ascend/enginex-ascend-910-llama.cpp
10
0
Fork 0
Code Issues Pull Requests Actions 4 Projects Releases Wiki Activity

ggml : drop support for QK_K=64 (#7473)

Browse Source 
* ggml : drop support for QK_K=64

ggml-ci

* opencl : restore QK_K=256 define
This commit is contained in:
Georgi Gerganov
2024-05-23 10:00:21 +03:00
committed by GitHub
parent 1b1e27cb49
commit e84b71c2c6
16 changed files with 26 additions and 4049 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
Makefile
View File

@@ -389,10 +389,6 @@ else
MK_CXXFLAGS += -march=rv64gcv -mabi=lp64d
endif
ifdef LLAMA_QKK_64
MK_CPPFLAGS += -DGGML_QKK_64
endif
ifndef LLAMA_NO_ACCELERATE
# Mac OS - include Accelerate framework.
# `-framework Accelerate` works both with Apple Silicon and Mac Intel