changedC++
Llama.cpp with the Rockchip NPU integration as a GGML backend.
View on GitHub ↗unchangedC++
Llama.cpp with the Rockchip NPU integration as a GGML backend, run on Orange Pi 5
View on GitHub ↗changedC++
Llama.cpp with the Rockchip NPU integration as a GGML backend.
View on GitHub ↗unchangedC++
Llama.cpp with the Rockchip NPU integration as a GGML backend.
View on GitHub ↗unchangedC++
Llama.cpp with the Rockchip NPU integration as a GGML backend.
View on GitHub ↗unchangedC++
Llama.cpp with the Rockchip NPU integration as a GGML backend.
View on GitHub ↗unchangedC++
Llama.cpp with the Rockchip NPU integration as a GGML backend.
View on GitHub ↗unchangedC++
Llama.cpp with the Rockchip NPU integration as a GGML backend.
View on GitHub ↗unchangedC++
Llama.cpp with the Rockchip NPU integration as a GGML backend.
View on GitHub ↗unchangedC++
3588NPU Llama.cpp with the Rockchip NPU integration as a GGML backend.
View on GitHub ↗changedC++
llama.cpp on the Rockchip RK3588 NPU - RKNPU2 backend by @invisiofficial, rebased onto current upstream, with MoE experts on the NPU, cross-board tensor parallelism and a measurement study
View on GitHub ↗unchangedC++
Llama.cpp with the Rockchip NPU integration as a GGML backend.
View on GitHub ↗C++
Llama.cpp with the Rockchip NPU integration as a GGML backend.
View on GitHub ↗C++
Llama.cpp with the Rockchip NPU integration as a GGML backend.
View on GitHub ↗C++
Llama.cpp with the Rockchip NPU integration as a GGML backend.
View on GitHub ↗C++
Llama.cpp with the Rockchip NPU integration as a GGML backend.
View on GitHub ↗C++
Llama.cpp with the Rockchip NPU integration as a GGML backend.
View on GitHub ↗C++
Llama.cpp with the Rockchip NPU integration as a GGML backend.
View on GitHub ↗C++
Llama.cpp with the Rockchip NPU integration as a GGML backend.
View on GitHub ↗C++
Llama.cpp with the Rockchip NPU integration as a GGML backend.
View on GitHub ↗C++
Llama.cpp with the Rockchip NPU integration as a GGML backend.
View on GitHub ↗C++
Llama.cpp with the Rockchip NPU integration as a GGML backend.
View on GitHub ↗C++
Llama.cpp with the Rockchip NPU integration as a GGML backend.
View on GitHub ↗C++
Llama.cpp with the Rockchip NPU integration as a GGML backend.
View on GitHub ↗C++
Llama.cpp with the Rockchip NPU integration as a GGML backend.
View on GitHub ↗C++
Llama.cpp with the Rockchip NPU integration as a GGML backend.
View on GitHub ↗C++
Llama.cpp with the Rockchip NPU integration as a GGML backend.
View on GitHub ↗C++
Llama.cpp with the Rockchip NPU integration as a GGML backend.
View on GitHub ↗C++
Llama.cpp with the Rockchip NPU integration as a GGML backend.
View on GitHub ↗C++
Llama.cpp with the Rockchip NPU integration as a GGML backend.
View on GitHub ↗C++
Llama.cpp with the Rockchip NPU integration as a GGML backend.
View on GitHub ↗C++
Llama.cpp with the Rockchip NPU integration as a GGML backend.
View on GitHub ↗C++
Llama.cpp with the Rockchip NPU integration as a GGML backend.
View on GitHub ↗C++
Llama.cpp with the Rockchip NPU integration as a GGML backend.
View on GitHub ↗C++
Llama.cpp with the Rockchip NPU integration as a GGML backend.
View on GitHub ↗C++
Llama.cpp with the Rockchip NPU integration as a GGML backend.
View on GitHub ↗C++
Llama.cpp with the Rockchip NPU integration as a GGML backend.
View on GitHub ↗C++
Llama.cpp with the Rockchip NPU integration as a GGML backend.
View on GitHub ↗C++
Llama.cpp with the Rockchip NPU integration as a GGML backend.
View on GitHub ↗C++
Llama.cpp with the Rockchip NPU integration as a GGML backend.
View on GitHub ↗C++
Llama.cpp with the Rockchip NPU integration as a GGML backend.
View on GitHub ↗C++
Llama.cpp with the Rockchip NPU integration as a GGML backend.
View on GitHub ↗C++
Llama.cpp with the Rockchip NPU integration as a GGML backend.
View on GitHub ↗C++
Llama.cpp with the Rockchip NPU integration as a GGML backend.
View on GitHub ↗C++
Llama.cpp with the Rockchip NPU integration as a GGML backend.
View on GitHub ↗
Comments (0)