xiangyangkan

faster-bert-as-service

Using TensorRT and Triton Server to build BERT model as a service

hnsw-gpu

GPU implementation of Hierarchical Navigable Small World (HNSW) graph algorithm for Python

jupyterlab

remote access to jupyterlab via ssh or http

bandwidth-calculator

bandwidth calculator for HDMI OR DP

BELLE

BELLE: Be Everyone's Large Language model Engine（开源中文对话大模型）

boyu

boyu learning

Chinese-LLaMA-Alpaca-2

中文 LLaMA-2 & Alpaca-2 大模型二期项目 (Chinese LLaMA-2 & Alpaca-2 LLMs)

FasterTransformer

Transformer related optimization, including BERT, GPT

Firefly

Firefly(流萤): 中文对话式大语言模型(全量微调+QLoRA)，支持微调Baichuan2、CodeLlama、Llma2、Llama、Qwen、Baichuan、ChatGLM2、InternLM、Ziya、Bloom等大模型

gpu-learning

pid

PID controller of boil pressure

LLMZoo

⚡LLM Zoo is a project that provides data, models, and evaluation benchmark for large language models.⚡

lm-evaluation-harness

Add DeepSpeed & Megatron Inference Support

Megatron-DeepSpeed

Ongoing research training transformer language models at scale, including: BERT & GPT-2

NeMo

NeMo: a toolkit for conversational AI

nextjs-notion-starter-kit

Deploy your own Notion-powered website in minutes with Next.js and Vercel.

NotionNext

使用 NextJS + Notion API 实现的，支持多种部署方案的静态博客，无需服务器、零门槛搭建网站，为Notion和所有创作者设计。 (A static blog built with NextJS and Notion API, supporting multiple deployment options. No server required, zero threshold to set up a website. Designed for Notion and all creators.)

TensorRT

NVIDIA® TensorRT™, an SDK for high-performance deep learning inference, includes a deep learning inference optimizer and runtime that delivers low latency and high throughput for inference applications.

text-generation-webui

A Gradio web UI for Large Language Models. Supports transformers, GPTQ, llama.cpp (ggml), Llama models.

zerotier-planet-builder

A ZeroTierOne planet with zero-ui web interface docker image builder.