av1d / rk3588_npu_llm_server
Allows access via HTTP to LLM running on RK3588 NPU. Returns JSON response.
☆20Updated 8 months ago
Alternatives and similar repositories for rk3588_npu_llm_server:
Users that are interested in rk3588_npu_llm_server are comparing it to the libraries listed below
- Web chat front end for rk3588_npu_llm_server / RK3588 LLM chat interface☆11Updated 6 months ago
- Easy usage of Rockchip's NPUs found in RK3588 and similar chips☆111Updated 2 months ago
- Easier usage of LLMs in Rockchip's NPU on SBCs like Orange Pi 5 and Radxa Rock 5 series☆100Updated 2 months ago
- Run Large Language Models on RK3588 with GPU-acceleration☆89Updated last year
- Streaming TTS based on Piper with optional RK3588 NPU support☆62Updated last month
- top-like script for rockhip NPUs on linux☆32Updated 2 months ago
- 将LLM 模型部署到 Rockchip Rk3588芯片中,在开发板上使用NPU进行推理☆22Updated 3 months ago
- ☆517Updated last month
- YoloV5 NPU for the RK3566/68/88☆88Updated 7 months ago
- Radxa Zero 3W/E image with Ubuntu 22, OpenCV, deep learning frameworks and NPU drivers☆24Updated 8 months ago
- MLC Stable Diffusion for RK3588's Mali GPU☆40Updated 4 months ago
- openFyde supported hardware RADXA Rock5 Model B build artefacts and pre-built image releases.☆36Updated last month
- Useful resources for developing with the RK3588.☆236Updated 2 months ago
- Inference RWKV v5, v6 and (WIP) v7 with Qualcomm AI Engine Direct SDK☆49Updated last week
- Automated script to convert Huggingface and GGUF models to rkllm format for running on Rockchip NPU☆15Updated 2 months ago
- ☆27Updated last month
- PLEASE USE https://github.com/nyanmisaka/ffmpeg-rockchip REPO INSTEAD.☆90Updated 10 months ago
- Superresolution running on Rockchip NPU (RK3588, etc..)☆12Updated 6 months ago
- YoloV10 for a bare Raspberry Pi 4 or 5☆22Updated 7 months ago
- Rockchip系SoCのHWエンコーダ(rkmpp)の性能実験☆89Updated last week
- ffmpeg->rockchip mpp decoding->rknpu rknn->opencv opengl rendering☆35Updated 2 years ago
- Examples of AI model running on the board, such as horizon/rockchip and so on.☆19Updated last year
- The rknn2 API uses the secondary encapsulation of the process, which is easy for everyone to call. It is applicable to rk356x rk3588☆44Updated 2 years ago
- YoloV8 NPU for the RK3566/68/88☆47Updated 7 months ago
- ☆32Updated 6 months ago
- YOLOv5 for RK3588☆76Updated last year
- ☆13Updated last year
- Reverse engineering the rk3588 npu☆71Updated 8 months ago
- ☆25Updated 7 months ago
- [ICLR 2020] Lite Transformer with Long-Short Range Attention☆12Updated 2 years ago