tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-07-23 11:16:32 +00:00
Code Issues Packages Projects Releases Wiki Activity

Convert vector to f16 for dequantize mul mat vec (#1913)

Browse Source 
* Convert vector to f16 for dmmv

* compile option

* Added compilation option description to README

* Changed cmake CUDA_ARCHITECTURES from "OFF" to "native"
This commit is contained in:
Johannes Gäßler
2023-06-19 10:23:56 +02:00
committed by GitHub
parent b24c3049d9
commit 16b9cd1939
5 changed files with 158 additions and 68 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
Makefile
View File

@ -169,6 +169,9 @@ ifdef LLAMA_CUDA_DMMV_Y
else
NVCCFLAGS += -DGGML_CUDA_DMMV_Y=1
endif # LLAMA_CUDA_DMMV_Y
ifdef LLAMA_CUDA_DMMV_F16
NVCCFLAGS += -DGGML_CUDA_DMMV_F16
endif # LLAMA_CUDA_DMMV_F16
ifdef LLAMA_CUDA_KQUANTS_ITER
NVCCFLAGS += -DK_QUANTS_PER_ITERATION=$(LLAMA_CUDA_KQUANTS_ITER)
else