• 1
• 0
• 0

candle-gcu

• 1
• 0
• 0

nvtop

GPU & Accelerator process monitoring for AMD, Apple, Huawei, Intel, NVIDIA and Qualcomm

• 1
• 0
• 0

DeepSpeed

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

• 1
• 0
• 0

Ubridge

Bridge between ML frameworks and underlying computing interface.

• 1
• 1
• 0

candle-vllm

Efficent platform for inference and serving local LLMs including an OpenAI compatible API server.

• 1
• 0
• 0

CICD

• 1
• 0
• 0

UHHI

• 1
• 5
• 0

vllm-gcu

基于原生 vLLM 框架适配 Enflame GCU（S60）推出的大模型推理系统

• 1
• 0
• 0

candle-vllm-gcu

面向燧原GCU平台的大语言模型推理与聊天服务框架，其基于 Candle-GCU 和 开源项目Candle-vLLM 实现，兼容OpenAI API接口。

• 1
• 0
• 0

candle

Minimalist ML framework for Rust

• 1
• 0
• 0

eigen

• 1
• 0
• 0

test2

• 1
• 0
• 0

test

Just for test

• 1
• 1
• 0

gcushare

在 Kubernetes 集群中运行启用了Enflame GCU 共享的容器

• 1
• 0
• 0

gcu-exporter

• 1
• 0
• 0

sccache

Sccache is a ccache-like tool. It is used as a compiler wrapper and avoids compilation when possible. Sccache has the capability to utilize caching...

• 1
• 0
• 0

tops-codec-headers

有关燧原科技topscodec编解码ffmpeg插件头文件

• 1
• 0
• 0

ccache

ccache – a fast compiler cache

• 1
• 1
• 1

FFmpeg-GCU

有关燧原科技 topscodec 编解码 FFmpeg 插件

• 1
• 0
• 0

ci-demo

just a demo repo for ci pipeline -> internal runner/executor