Alternatives and similar repositories for bitsandbytes-rocm

Users that are interested in bitsandbytes-rocm are comparing it to the libraries listed below

• arlo-phoenix / bitsandbytes-rocm-5.6
  8-bit CUDA functions for PyTorch Rocm compatible
  ☆41Updated last year
• jllllll / exllama
  A more memory-efficient rewrite of the HF transformers implementation of Llama for use with quantized weights.
  ☆64Updated 2 years ago
• johnsmith0031 / alpaca_lora_4bit
  ☆535Updated 2 years ago
• Gryphe / MergeMonster
  An unsupervised model merging algorithm for Transformers-based language models.
  ☆108Updated last year
• harrisonvanderbyl / rwkv-cpp-accelerated
  A torchless, c++ rwkv implementation using 8bit quantization, written in cuda/hip/vulkan for maximum compatibility and minimum dependenci…
  ☆313Updated 2 years ago
• Silver267 / pytorch-to-safetensor-converter
  A simple converter which converts pytorch bin files to safetensor, intended to be used for LLM conversion.
  ☆72Updated 2 years ago
• oobabooga / GPTQ-for-LLaMa
  4 bits quantization of LLaMa using GPTQ
  ☆131Updated 2 years ago
• iantbutler01 / rwkv-raven-qlora-4bit-instruct
  A finetuning pipeline for instruct tuning Raven 14bn using QLORA 4bit and the Ditty finetuning library
  ☆28Updated last year
• AlpinDale / RPTQ-for-LLaMA
  Efficient 3bit/4bit quantization of LLaMA models
  ☆18Updated 2 years ago
• ROCm / bitsandbytes
  8-bit CUDA functions for PyTorch
  ☆70Updated 4 months ago
• broncotc / bitsandbytes-rocm
  ☆36Updated 2 years ago
• jllllll / llama-cpp-python-cuBLAS-wheels
  Wheels for llama-cpp-python compiled with cuBLAS support
  ☆102Updated 2 years ago
• aspctu / alpaca-lora
  Instruct-tuning LLaMA on consumer hardware
  ☆66Updated 2 years ago
• Gryphe / BlockMerge_Gradient
  Merge Transformers language models by use of gradient parameters.
  ☆213Updated last year
• EmbeddedLLM / vllm
  vLLM: A high-throughput and memory-efficient inference and serving engine for LLMs
  ☆93Updated this week
• eugenepentland / landmark-attention-qlora
  Landmark Attention: Random-Access Infinite Context Length for Transformers QLoRA
  ☆125Updated 2 years ago
• pointnetwork / point-alpaca
  ☆404Updated 2 years ago
• cmp-nct / ggllm.cpp
  Falcon LLM ggml framework with CPU and GPU support
  ☆249Updated 2 years ago
• olealgoritme / gddr6
  Linux​ based GDDR6/GDDR6X VRAM temperature reader for NVIDIA RTX 3000/4000 series GPUs.
  ☆109Updated 9 months ago
• xor2k / gpu_undervolt
  ☆49Updated 2 years ago
• ROCm / flash-attention
  Fast and memory-efficient exact attention
  ☆214Updated this week
• randaller / llama-cpu
  Inference on CPU code for LLaMA models
  ☆137Updated 2 years ago
• turboderp-org / exui
  Web UI for ExLlamaV2
  ☆513Updated last year
• wawawario2 / long_term_memory
  A gradio web UI for running Large Language Models like GPT-J 6B, OPT, GALACTICA, LLaMA, and Pygmalion.
  ☆310Updated 2 years ago
• 0cc4m / KoboldAI
  ☆156Updated 2 years ago
• 0cc4m / GPTQ-for-LLaMa
  4 bits quantization of LLMs using GPTQ
  ☆49Updated 2 years ago
• FailSpy / abliterator
  Simple Python library/structure to ablate features in LLMs which are supported by TransformerLens
  ☆569Updated last year
• WapaMario63 / GPTQ-for-LLaMa-ROCm
  4 bits quantization of LLaMA using GPTQ, ported to HIP for use in AMD GPUs.
  ☆32Updated 2 years ago
• hizkifw / WebChatRWKVstic
  ChatGPT-like Web UI for RWKVstic
  ☆100Updated 2 years ago
• aikitoria / open-gpu-kernel-modules
  NVIDIA Linux open GPU with P2P support
  ☆129Updated this week