pepesi
Follow
Stars
Official implementation of ICML 2024 paper "ExCP: Extreme LLM Checkpoint Compression via Weight-Momentum Joint Shrinking".
OpenAI 接口管理 & 分发系统，支持 Azure、Anthropic Claude、Google PaLM 2 & Gemini、智谱 ChatGLM、百度文心一言、讯飞星火认知、阿里通义千问、360 智脑以及腾讯混元，可用于二次分发管理 key，仅单可执行文件，已打包好 Docker 镜像，一键部署，开箱即用. OpenAI key management & redistributi…
A QoS-based scheduling system brings optimal layout and status to workloads such as microservices, web services, big data jobs, AI jobs, etc.
HAMi-core compiles libvgpu.so, which ensures hard limit on GPU in container
OpenAIOS vGPU device plugin for Kubernetes is originated from the OpenAIOS project to virtualize GPU device memory, in order to allow applications to access larger memory space than its physical ca…
A Huggingface proxy deployed on Cloudflare Workers, tailored for Chinese users. 🌐🚀
CSGHub is an opensource large model assets platform just like on-premise huggingface which helps to manage datasets, model files, codes and more. CSGHub是一个开源、可信的大模型资产管理平台，可帮助用户治理LLM和LLM应用生命周期中涉及到的资…
Unify Efficient Fine-Tuning of 100+ LLMs
OpenID Connect (OIDC) identity and OAuth 2.0 provider with pluggable connectors
🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
C++ implementation of ChatGLM-6B & ChatGLM2-6B & ChatGLM3 & GLM4
A Cloud Native Batch System (Project under CNCF)
QLoRA: Efficient Finetuning of Quantized LLMs
Cloud native networking and network security
AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.
K8s 集群证书过期处理，更新 kubeadm 生成的证书有效期为 10 年。支持全部版本。
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.