ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-04-23 16:09:18 +00:00
Code Issues Packages Projects Releases Wiki Activity

Enable q6_0 for flash attention (#101)

Browse Source 
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
This commit is contained in:
Kawrakow
2024-10-22 11:34:49 +02:00
committed by GitHub
parent 7c5a91daf1
commit 0f3a424166
11 changed files with 120 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
Makefile
View File

@@ -600,6 +600,8 @@ else
OBJ_CUDA_TMPL += $(patsubst %.cu,%.o,$(wildcard ggml/src/ggml-cuda/template-instances/fattn-vec*f16-f16.cu))
OBJ_CUDA_TMPL += $(patsubst %.cu,%.o,$(wildcard ggml/src/ggml-cuda/template-instances/fattn-vec*q8_0-iq4_nl.cu))
OBJ_CUDA_TMPL += $(patsubst %.cu,%.o,$(wildcard ggml/src/ggml-cuda/template-instances/fattn-vec*:iq4_nl-iq4_nl.cu))
OBJ_CUDA_TMPL += $(patsubst %.cu,%.o,$(wildcard ggml/src/ggml-cuda/template-instances/fattn-vec*:q6_0-q5_0.cu))
OBJ_CUDA_TMPL += $(patsubst %.cu,%.o,$(wildcard ggml/src/ggml-cuda/template-instances/fattn-vec*:q8_0-q6_0.cu))
endif # GGML_CUDA_FA_ALL_QUANTS
ifdef GGML_CUDA