-
Notifications
You must be signed in to change notification settings - Fork 87
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
[BUG] Fail to run llama v2 7B quantized on Galaxy S24 Ultra using GENIE C API #102
Comments
hi pal |
I think I have found the reason, need to set adsp path as well,like this, in your app jni part
=========================== |
Hi @Harrison-niu DId you succeed to run it on S24 ? |
I ran the app on QCS8550,not on S24,but I don't think S24 has something speccial since genei-run already succeeds.
|
Same issue here, using SM8650, Snapdragon 8 gen 3 , QIDK |
2023-09-20 22:55:39.269 1573-1573 qspmHal vendor.qti.qspmhal-service I cpuProfName:com.quicinc.chatapp-cpu - cpu_prof_info.path:/data/vendor/gaming/com.quicinc.chatapp-cpu |
Hi,
Android NDK Application (using GENIE C API) fails to run llama v2 7B quantized on Galaxy S24 Ultra.
It succeeds to create the dialog config. (GenieDialogConfig_createFromJson).
But, it fails to create the dialog. (GenieDialog_create).
The error msg is following.
How can fix it ?
Log
The command "genie-t2t-run" is working well on S24 Ultra.
The text was updated successfully, but these errors were encountered: