Skip to content

Commit 76abeee

Browse files
authored
Update Makefile to support MOE
In reference to ggml-org/llama.cpp#4406 Need a newer version of llama.cpp to handle MoE models, such as Mixtral 8x7b Signed-off-by: Samuel Walker <[email protected]>
1 parent fb6a5bc commit 76abeee

File tree

1 file changed

+1
-1
lines changed

1 file changed

+1
-1
lines changed

Makefile

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -8,7 +8,7 @@ GOLLAMA_VERSION?=aeba71ee842819da681ea537e78846dc75949ac0
88

99
GOLLAMA_STABLE_VERSION?=50cee7712066d9e38306eccadcfbb44ea87df4b7
1010

11-
CPPLLAMA_VERSION?=8a7b2fa528f130631a5f43648481596ab320ed5a
11+
CPPLLAMA_VERSION?=799a1cb13b0b1b560ab0ceff485caed68faa8f1f
1212

1313
# gpt4all version
1414
GPT4ALL_REPO?=https://github.com/nomic-ai/gpt4all

0 commit comments

Comments
 (0)