Closed realcarlos closed 11 months ago
This models works fine.
FYI: q2_k is not working in my tests, I got bad_alloc
crash or unexpectedly reached end of file
(enabling Extended Virtual Addressing
). q4_0 works fine.
I also trying integrate llama.cpp to my iOS apps (latest commit), the problem is looks same with here.
FYI: q2_k is not working in my tests, I got
bad_alloc
crash orunexpectedly reached end of file
(enablingExtended Virtual Addressing
). q4_0 works fine.I also trying integrate llama.cpp to my iOS apps (latest commit), the problem is looks same with here.
In the current version of llmfarm, I use this commit. q2_k works fine on iphone(without metal) and Mac.
FYI: q2_k is not working in my tests, I got
bad_alloc
crash orunexpectedly reached end of file
(enablingExtended Virtual Addressing
). q4_0 works fine.I also trying integrate llama.cpp to my iOS apps (latest commit), the problem is looks same with here.
You may have compiled llmfarm_core with -DGGML_QKK_64 in Package.swift. You need to rebuild the project without this flag, or requantize the models for QKK_64.
if someone makes a ggml version