Imagineee<p>I just got llama2.c running on the Milk V Duo. Compiled using the offical Milk V toolchain. Used the smallest stories15M model and took about 10 minutes or so (I didn't count) to generate.<br>However, this is only running on the cpu, with the built in npu we might get faster speeds, but that is outside the the reaches of my brain.</p><p><a href="https://mastodon.social/tags/llama2" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>llama2</span></a> <a href="https://mastodon.social/tags/milkv" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>milkv</span></a> <a href="https://mastodon.social/tags/milkvduo" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>milkvduo</span></a> <a href="https://mastodon.social/tags/riscv" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>riscv</span></a></p>