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
  ☆1,045Updated 2 months ago
• NousResearch / DisTrO
  Distributed Training Over-The-Internet
  ☆951Updated 2 months ago
• mirage-project / mirage
  Mirage: Automatically Generating Fast GPU Kernels without Programming in Triton/CUDA
  ☆1,647Updated last week
• HazyResearch / ThunderKittens
  Tile primitives for speedy kernels
  ☆2,555Updated last week
• turboderp-org / exllamav2
  A fast inference library for running LLMs locally on modern consumer-class GPUs
  ☆4,258Updated 3 weeks ago
• ikawrakow / ik_llama.cpp
  llama.cpp fork with additional SOTA quants and improved performance
  ☆964Updated last week
• tinygrad / 7900xtx
  ☆449Updated 4 months ago
• PrimeIntellect-ai / OpenDiloco
  OpenDiLoCo: An Open-Source Framework for Globally Distributed Low-Communication Training
  ☆521Updated 6 months ago
• intentee / paddler
  Stateful load balancer custom-tailored for llama.cpp 🏓🦙
  ☆800Updated last week
• mobiusml / hqq
  Official implementation of Half-Quadratic Quantization (HQQ)
  ☆856Updated this week
• aphrodite-engine / aphrodite-engine
  Large-scale LLM inference engine
  ☆1,502Updated this week
• Cornell-RelaxML / quip-sharp
  ☆549Updated 9 months ago
• tspeterkim / flash-attention-minimal
  Flash Attention in ~100 lines of CUDA (forward pass only)
  ☆897Updated 7 months ago
• IST-DASLab / marlin
  FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.
  ☆870Updated 11 months ago
• philipturner / metal-flash-attention
  FlashAttention (Metal Port)
  ☆514Updated 10 months ago
• punica-ai / punica
  Serving multiple LoRA finetuned LLM as one
  ☆1,082Updated last year
• mlecauchois / micrograd-cuda
  ☆249Updated last year
• PrimeIntellect-ai / prime
  prime is a framework for efficient, globally distributed training of AI models over the internet.
  ☆786Updated 2 months ago
• microsoft / VPTQ
  VPTQ, A Flexible and Extreme low-bit quantization algorithm
  ☆648Updated 3 months ago
• flashinfer-ai / flashinfer
  FlashInfer: Kernel Library for LLM Serving
  ☆3,474Updated this week
• google-deepmind / recurrentgemma
  Open weights language model from Google DeepMind, based on Griffin.
  ☆645Updated 2 months ago
• aikitoria / open-gpu-kernel-modules
  NVIDIA Linux open GPU with P2P support
  ☆28Updated last week
• Juice-Labs / Juice-Labs
  Juice Community Version Public Release
  ☆598Updated 3 months ago
• turboderp-org / exllamav3
  An optimized quantization and inference library for running LLMs locally on modern consumer-class GPUs
  ☆466Updated this week
• AnswerDotAI / fsdp_qlora
  Training LLMs with QLoRA + FSDP
  ☆1,526Updated 9 months ago
• zeux / calm
  CUDA/Metal accelerated language model inference
  ☆599Updated 2 months ago
• mit-han-lab / TinyChatEngine
  TinyChatEngine: On-Device LLM Inference Library
  ☆882Updated last year
• PaulPauls / llama3_interpretability_sae
  A complete end-to-end pipeline for LLM interpretability with sparse autoencoders (SAEs) using Llama 3.2, written in pure PyTorch and full…
  ☆622Updated 4 months ago
• turboderp / exllama
  A more memory-efficient rewrite of the HF transformers implementation of Llama for use with quantized weights.
  ☆2,894Updated last year
• likejazz / llama3.np
  llama3.np is a pure NumPy implementation for Llama 3 model.
  ☆987Updated 3 months ago