Mixtral: CUDA error 1 at D:\a\llama.cpp\llama.cpp\ggml-cuda.cu:8893: invalid argument

[LostRuins]

In build = 1686 (48b24b1), I am getting a CUDA error, which seems to have been introduced around https://github.com/ggerganov/llama.cpp/blob/d232aca5a73b290e218a2e48b91023d5e994203f/llama.cpp

Using my RTX2060, testing mixtral-8x7b-instruct-v0.1.Q3_K_M.gguf

.\main.exe -m e:\LLaMA\models\mixtral-8x7b-instruct-v0.1.Q3_K_M.gguf -b 512 -n 10 -p "A website works by having pages, which are made of HTML code. This code tells your computer how to display the content on each page you visit - whether it's an image or text file (like PDFs). In order for someone else's browser not only be able but also want those same results when accessing any given URL; some additional steps need taken by way of programming scripts that will add functionality such as making links clickable! The most common type is called static HTML pages because they remain unchanged over time unless modified manually (either through editing files directly or using an interface such as WordPress). They are usually served up via HTTP protocols - this means anyone can access them without having any special privileges like being part of a group who is allowed into restricted areas online; however, there may still exist some limitations depending upon where one lives geographically speaking."

Before processing starts, the program crashes.

CUDA error 1 at D:\a\llama.cpp\llama.cpp\ggml-cuda.cu:8893: invalid argument
current device: 0
GGML_ASSERT: D:\a\llama.cpp\llama.cpp\ggml-cuda.cu:8893: !"CUDA error"

[Ttl]

should already be fixed by #4599

[LostRuins]

Seems to be fixed.