Skip to content

0.10.1
Compare
Choose a tag to compare
@b4rtaz b4rtaz released this 28 Jul 14:29
· 33 commits to main since this release
v0.10.1
2339746

Implemented the fallback implementation for the matmulQ40vQ80 operation. Distributed Llama now supports all CPU architectures, with optimizations specifically for ARM and AVX2 CPUs.

Assets 2
Loading