inference/research
verifiedhigh · 0.95updated 2026-10-03

KTransformers GitHub repository

repo

Fields

id
sources/engine-ktransformers-github
Publisher
kvcache-ai
Kind
repo
Accessed
2026-10-03
notes
KTransformers repo README: CPU-GPU heterogeneous inference, expert offload to CPU, Ascend NPU support with CPU expert offload, AVX512/AVX2 CPU backends.

Notes

KTransformers repo README: CPU-GPU heterogeneous inference, expert offload to CPU, Ascend NPU support with CPU expert offload, AVX512/AVX2 CPU backends.

Cross-references

This record references no other records.