banjuede

banjuede's Stars

• leptonai/gpud

  Language:Go16810

• kubernetes/kubernetes

  Production-Grade Container Scheduling and Management

  Language:Go110k39.4k

• ray-project/kuberay

  A toolkit to run Ray applications on Kubernetes

  Language:Go1.2k373

• liguodongiot/llm-action

  本项目旨在分享大模型相关技术原理以及实战经验。

  Language:HTML9.4k920

• apple/ToolSandbox

  Language:Python11715

• karmada-io/karmada

  Open, Multi-Cloud, Multi-Cluster Kubernetes Orchestration

  Language:Go4.4k875

• coreweave/nccl-tests

  NVIDIA NCCL Tests for Distributed Training

  Language:Shell6115

• anthropics/hh-rlhf

  Human preference data for "Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback"

  1.6k121

• haotian-liu/LLaVA

  [NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

  Language:Python19.6k2.2k

• hpcaitech/Open-Sora

  Open-Sora: Democratizing Efficient Video Production for All

  Language:Python21.8k2.1k

• mamba-org/mamba

  The Fast Cross-Platform Package Manager

  Language:C++6.8k349

• state-spaces/mamba

  Mamba SSM architecture

  Language:Python12.7k1.1k

• predibase/lorax

  Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs

  Language:Python2.1k140

• vllm-project/vllm

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

  Language:Python27.9k4.1k

• ollama/ollama

  Get up and running with Llama 3.2, Mistral, Gemma 2, and other large language models.

  Language:Go92.1k7.3k

• flashinfer-ai/flashinfer

  FlashInfer: Kernel Library for LLM Serving

  Language:Cuda1.2k115

• BlinkDL/RWKV-LM

  RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.

  Language:Python12.5k847

• AUTOMATIC1111/stable-diffusion-webui

  Stable Diffusion web UI

  Language:Python141k26.6k

• hiyouga/LLaMA-Factory

  Efficiently Fine-Tune 100+ LLMs in WebUI (ACL 2024)

  Language:Python31.9k3.9k

• TaskingAI/TaskingAI

  The open source platform for AI-native application development.

  Language:Python6.1k299

• microsoft/TaskWeaver

  A code-first agent framework for seamlessly planning and executing data analytics tasks.

  Language:Python5.2k663

• codykrieger/gfxCardStatus

  gfxCardStatus is an open-source menu bar application that keeps track of which graphics card your unibody, dual-GPU MacBook Pro is using at any given time, and allows you to switch between them on demand.

  Language:Objective-C1.7k322

• punica-ai/punica

  Serving multiple LoRA finetuned LLM as one

  Language:Python96445

• facebook/rocksdb

  A library that provides an embeddable, persistent key-value store for fast storage.

  Language:C++28.4k6.3k

• facebookresearch/NeuralDB

  Database Reasoning Over Text project for ACL paper

  Language:Python35348

• apache/fury

  A blazingly fast multi-language serialization framework powered by JIT and zero-copy.

  Language:Java3k225

• notion-enhancer/notion-enhancer

  An enhancer/customiser for the all-in-one productivity workspace Notion

  Language:JavaScript4.8k242

• aimhubio/aim

  Aim 💫 — An easy-to-use & supercharged open-source experiment tracker.

  Language:Python5.2k316

• cumulo-autumn/StreamDiffusion

  StreamDiffusion: A Pipeline-Level Solution for Real-Time Interactive Generation

  Language:Python9.5k682

• Dao-AILab/flash-attention

  Fast and memory-efficient exact attention

  Language:Python13.6k1.3k