nicolas
/
ik_llama_opt
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Enable all CPU-backend FA supported quants by default (#1549)

This commit is contained in:
Kawrakow 2026-03-29 14:36:09 +02:00 committed by GitHub
parent bc2c74c9db
commit 3fa98d3213
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
ggml/CMakeLists.txt
View File

@ -139,7 +139,7 @@ set (GGML_CUDA_COMPRESSION_MODE "size" CACHE STRING
set_property(CACHE GGML_CUDA_COMPRESSION_MODE PROPERTY STRINGS "none;speed;balance;size")
option(GGML_IQK_FLASH_ATTENTION "ggml: enable the IQK FlashAttention CPU kernels" ON)
option(GGML_IQK_FA_ALL_QUANTS "ggml: compile all quants for IQK FlashAttention" OFF)
option(GGML_IQK_FA_ALL_QUANTS "ggml: compile all quants for IQK FlashAttention" ON)
option(GGML_CURL "ggml: use libcurl to download model from an URL" OFF)
option(GGML_HIPBLAS "ggml: use hipBLAS" OFF)