Alternatives and similar repositories for open-gpu-kernel-modules

Users that are interested in open-gpu-kernel-modules are comparing it to the libraries listed below

• mikex86 / LibreCuda
  ☆1,066Updated 5 months ago
• NousResearch / DisTrO
  Distributed Training Over-The-Internet
  ☆963Updated last month
• mirage-project / mirage
  Mirage Persistent Kernel: Compiling LLMs into a MegaKernel
  ☆1,942Updated this week
• HazyResearch / ThunderKittens
  Tile primitives for speedy kernels
  ☆2,873Updated last week
• tinygrad / 7900xtx
  ☆448Updated 7 months ago
• ikawrakow / ik_llama.cpp
  llama.cpp fork with additional SOTA quants and improved performance
  ☆1,315Updated this week
• punica-ai / punica
  Serving multiple LoRA finetuned LLM as one
  ☆1,114Updated last year
• tspeterkim / flash-attention-minimal
  Flash Attention in ~100 lines of CUDA (forward pass only)
  ☆968Updated 10 months ago
• turboderp-org / exllamav2
  A fast inference library for running LLMs locally on modern consumer-class GPUs
  ☆4,361Updated 2 months ago
• dropbox / hqq
  Official implementation of Half-Quadratic Quantization (HQQ)
  ☆889Updated 3 weeks ago
• Cornell-RelaxML / quip-sharp
  ☆565Updated last year
• microsoft / VPTQ
  VPTQ, A Flexible and Extreme low-bit quantization algorithm
  ☆663Updated 6 months ago
• aphrodite-engine / aphrodite-engine
  Large-scale LLM inference engine
  ☆1,583Updated this week
• IST-DASLab / marlin
  FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.
  ☆946Updated last year
• philipturner / metal-flash-attention
  FlashAttention (Metal Port)
  ☆549Updated last year
• intel / auto-round
  Advanced Quantization Algorithm for LLMs and VLMs, with support for CPU, Intel GPU, CUDA and HPU.
  ☆701Updated this week
• LeanModels / DFloat11
  DFloat11: Lossless LLM Compression for Efficient GPU Inference
  ☆559Updated 2 months ago
• b4rtaz / distributed-llama
  Distributed LLM inference. Connect home devices into a powerful cluster to accelerate LLM inference. More devices means faster inference.
  ☆2,735Updated last week
• ROCm / flash-attention
  Fast and memory-efficient exact attention
  ☆198Updated 3 weeks ago
• turboderp-org / exllamav3
  An optimized quantization and inference library for running LLMs locally on modern consumer-class GPUs
  ☆558Updated last week
• trholding / llama2.c
  Llama 2 Everywhere (L2E)
  ☆1,520Updated 2 months ago
• PrimeIntellect-ai / OpenDiloco
  OpenDiLoCo: An Open-Source Framework for Globally Distributed Low-Communication Training
  ☆546Updated 10 months ago
• mit-han-lab / TinyChatEngine
  TinyChatEngine: On-Device LLM Inference Library
  ☆921Updated last year
• PrimeIntellect-ai / prime-diloco
  prime is a framework for efficient, globally distributed training of AI models over the internet.
  ☆849Updated 5 months ago
• intel / intel-extension-for-transformers
  ⚡ Build your chatbot within minutes on your favorite device; offer SOTA compression techniques for LLMs; run LLMs efficiently on Intel Pl…
  ☆2,165Updated last year
• microsoft / T-MAC
  Low-bit LLM inference on CPU/NPU with lookup table
  ☆887Updated 5 months ago
• zeux / calm
  CUDA/Metal accelerated language model inference
  ☆622Updated 5 months ago
• Infini-AI-Lab / Sequoia
  scalable and robust tree-based speculative decoding algorithm
  ☆361Updated 9 months ago
• flashinfer-ai / flashinfer
  FlashInfer: Kernel Library for LLM Serving
  ☆4,062Updated this week
• likejazz / llama3.np
  llama3.np is a pure NumPy implementation for Llama 3 model.
  ☆991Updated 6 months ago