You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
See #2160 (comment) for more details.
Reverting to commit before 11f3ca0 resolves the issue.
Also, the workaround proposed in #2160 (comment) appears to work (at least for me).
Activity
mirek190 commentedon Aug 2, 2023
The same problem
My arguments - model is llama2 variant 13B
main --model models\new2\newhope.ggmlv3.q4_K_M.bin --mlock --color --threads 30 --keep -1 --batch_size 512 --n_predict -1 --top_k 10000 --top_p 0.9 --temp 0.96 --repeat_penalty 1.1 --ctx_size 4096 --interactive --instruct --reverse-prompt "### Human:" --reverse-prompt "### User:" --reverse-prompt "### Assistant:" -ngl 43
ggml-cuda.cu:4749: i01_high == rows_per_iter || g_device_count > 1
PS E:\LLAMA\llama.cpp>
without -ngl parameter is working.
dranger003 commentedon Aug 2, 2023
It appears PR #2480 solves this issue.
mirek190 commentedon Aug 2, 2023
Still not merged ....
dranger003 commentedon Aug 2, 2023
Confirmed latest commit 4f6b60c resolves the issue on my end.