TricorderO11y 最近的时间轴更新

llm-numbers-cn 中文版 llm-numbers

3k Orchestrating many small GPU clusters for running serverless GPU workloads

sxwl.ai SXWL.AI site

writing-assistant

docs.sxwl.ai 算想未来产品文档站点

a href="https://github.com/NascentCore/rag" target="_blank">rag Question and Answer based on Anything.

AiEditor AiEditor is a next-generation rich text editor for AI.

blog.sxwl.ai SXWL.AI's Blog Site

chat-ui

ChatGLM-6B ChatGLM-6B: An Open Bilingual Dialogue Language Model | 开源双语对话语言模型

ChatGLM-Efficient-Tuning Fine-tuning ChatGLM-6B with PEFT | 基于 PEFT 的高效 ChatGLM 微调

CMMLU CMMLU: Measuring massive multitask language understanding in Chinese

deep-learning-pytorch-huggingface

deepeval-inty

DeepSpeedExamples Example models using DeepSpeed

dockerfiles Deep Learning Dockerfiles

goctl modified goctl for 3k project

gpu-operator NVIDIA GPU Operator creates/configures/manages GPUs atop Kubernetes

graphrag_doubao 调整graphrag代码，接入豆包

inty-kotlin Inty SDK in Kotlin language, generated by Stainless.com

inty-python Inty python sdk

inty-typescript Inty typescript SDK

inty.cc Landing site of InTy, the portal to empathetic AI

kotlin-android-template Android + Kotlin + Github Actions + ktlint + Detekt + Gradle Kotlin DSL + buildSrc =

kserve Standardized Serverless ML Inference Platform on Kubernetes

langchain Build context-aware reasoning applications

license_manager

LLaMA LLaMA fine tune

mohe-code-obfuscator

MOSS An open-source tool-augmented conversational language model from Fudan University

my-unittest

nccl Optimized primitives for collective multi-GPU communication

network-operator Mellanox Network Operator

node-feature-discovery Node feature discovery for Kubernetes

OpenAI-RealtimeAPIDemoPythonPC A fork for realtime openai example

openebs-stack

P-tuning-v2 An optimized deep prompt tuning strategy comparable to fine-tuning across scales and tasks

runpod-python | Python library for RunPod API and serverless worker SDK.

SillyTavern LLM Frontend for Power Users.

sxwl-python-sdk

unit-test-writer A boilerplate for a GitHubb App webservice using gidgethub (> 4.1.0), aiohttp, and Heroku

vllm A high-throughput and memory-efficient inference and serving engine for LLMs

TricorderO11y 大模型算力云服务提供商   NascentCore.ai / CEO V2EX 第 584334 号会员，加入于 2022-06-10 13:11:36 +08:00

算想未来（https://nascentcore.ai）为中国 AI 经济打造世界领先的 AI IaaS Cloud，为中国大模型和 AI 应用开发者提供世界领先的基础设施软件服务。基于国产 GPU 的全新技术体系、构建独立自主可控的 AI IaaS Cloud，立足中国、服务全球大模型及 AI 应用开发者。