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
  ☆1,074Updated 8 months ago
• NousResearch / DisTrO
  Distributed Training Over-The-Internet
  ☆975Updated 3 months ago
• tinygrad / 7900xtx
  ☆451Updated 10 months ago
• HazyResearch / ThunderKittens
  Tile primitives for speedy kernels
  ☆3,120Updated this week
• ikawrakow / ik_llama.cpp
  llama.cpp fork with additional SOTA quants and improved performance
  ☆1,587Updated this week
• mirage-project / mirage
  Mirage Persistent Kernel: Compiling LLMs into a MegaKernel
  ☆2,104Updated last week
• punica-ai / punica
  Serving multiple LoRA finetuned LLM as one
  ☆1,140Updated last year
• dropbox / hqq
  Official implementation of Half-Quadratic Quantization (HQQ)
  ☆912Updated last month
• Cornell-RelaxML / quip-sharp
  ☆577Updated last year
• aphrodite-engine / aphrodite-engine
  Large-scale LLM inference engine
  ☆1,647Updated 2 weeks ago
• Juice-Labs / Juice-Labs
  Juice Community Version Public Release
  ☆628Updated 8 months ago
• tspeterkim / flash-attention-minimal
  Flash Attention in ~100 lines of CUDA (forward pass only)
  ☆1,067Updated last year
• turboderp-org / exllamav2
  A fast inference library for running LLMs locally on modern consumer-class GPUs
  ☆4,431Updated last month
• PrimeIntellect-ai / OpenDiloco
  OpenDiLoCo: An Open-Source Framework for Globally Distributed Low-Communication Training
  ☆562Updated last year
• google-deepmind / recurrentgemma
  Open weights language model from Google DeepMind, based on Griffin.
  ☆661Updated 2 weeks ago
• PrimeIntellect-ai / prime-diloco
  prime is a framework for efficient, globally distributed training of AI models over the internet.
  ☆850Updated 2 months ago
• microsoft / VPTQ
  VPTQ, A Flexible and Extreme low-bit quantization algorithm
  ☆674Updated 9 months ago
• intel / auto-round
  🎯An accuracy-first, highly efficient quantization toolkit for LLMs, designed to minimize quality degradation across Weight-Only Quantiza…
  ☆839Updated this week
• IST-DASLab / marlin
  FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.
  ☆1,005Updated last year
• ROCm / aiter
  AI Tensor Engine for ROCm
  ☆348Updated this week
• mit-han-lab / TinyChatEngine
  TinyChatEngine: On-Device LLM Inference Library
  ☆939Updated last year
• aikitoria / open-gpu-kernel-modules
  NVIDIA Linux open GPU with P2P support
  ☆126Updated 2 months ago
• ROCm / flash-attention
  Fast and memory-efficient exact attention
  ☆214Updated this week
• pytorch / ao
  PyTorch native quantization and sparsity for training and inference
  ☆2,657Updated last week
• philipturner / metal-flash-attention
  FlashAttention (Metal Port)
  ☆579Updated last year
• kolinko / effort
  An implementation of bucketMul LLM inference
  ☆224Updated last year
• trholding / llama2.c
  Llama 2 Everywhere (L2E)
  ☆1,526Updated 5 months ago
• apoorvumang / prompt-lookup-decoding
  ☆592Updated last year
• HazyResearch / Megakernels
  kernels, of the mega variety
  ☆665Updated last week
• intel / neural-speed
  An innovative library for efficient LLM inference via low-bit quantization
  ☆352Updated last year