- 👋 Hi, I’m @Leikoe
- 👀 I’m interested in programming accelerators / Machine learning.
- 🔥 Mainly using Python / C / Rust
- 📫 Reach me on discord : @leikowo
📐
no, you can't expect nvlink to work
Pinned Loading
-
tensoru
tensoru PublicMulti-backend accelerated tensor library with dynamic kernel generation.
Rust
-
Llama 3.2 inference in mlx - functio...
Llama 3.2 inference in mlx - functional style / no nn.Module 1# Uses entropix's tokenizer & downloaded weights. Saving this file into entropix's repo should work
23import math
4from typing import NamedTuple, List
5from pathlib import Path
-
-
-
Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page or contact support.
If the problem persists, check the GitHub status page or contact support.