experts4bit-qlora 0.37.4

T1Covered by 1 source · first reported by PyPI / crates.io / RubyGems / Go index / NuGet at 24 Sept, 21:54 UTC

Train and serve Mixture-of-Experts models that do not fit in VRAM: fused 4-bit experts, QLoRA, CPU/NVMe offload, and fast inference on consumer NVIDIA GPUs.

ai hardware releases

Sources

T1experts4bit-qlora 0.37.4PyPI / crates.io / RubyGems / Go index / NuGet24 Sept, 21:54