agrocylo / bitsandbytes-rocmLinks
8-bit CUDA functions for PyTorch, ported to HIP for use in AMD GPUs
☆51Updated 2 years ago
Alternatives and similar repositories for bitsandbytes-rocm
Users that are interested in bitsandbytes-rocm are comparing it to the libraries listed below
Sorting:
- 8-bit CUDA functions for PyTorch Rocm compatible☆41Updated last year
- 4 bits quantization of LLMs using GPTQ☆49Updated 2 years ago
- ☆535Updated last year
- An unsupervised model merging algorithm for Transformers-based language models.☆107Updated last year
- Falcon LLM ggml framework with CPU and GPU support☆247Updated last year
- 4 bits quantization of LLaMa using GPTQ☆130Updated 2 years ago
- 4 bits quantization of LLaMA using GPTQ, ported to HIP for use in AMD GPUs.☆32Updated last year
- A more memory-efficient rewrite of the HF transformers implementation of Llama for use with quantized weights.☆64Updated last year
- ☆37Updated 2 years ago
- A torchless, c++ rwkv implementation using 8bit quantization, written in cuda/hip/vulkan for maximum compatibility and minimum dependenci…☆313Updated last year
- A prompt/context management system☆170Updated 2 years ago
- Instruct-tuning LLaMA on consumer hardware☆66Updated 2 years ago
- Wheels for llama-cpp-python compiled with cuBLAS support☆98Updated last year
- A simple converter which converts pytorch bin files to safetensor, intended to be used for LLM conversion.☆71Updated last year
- Merge Transformers language models by use of gradient parameters.☆207Updated last year
- A gradio web UI for running Large Language Models like GPT-J 6B, OPT, GALACTICA, LLaMA, and Pygmalion.☆308Updated 2 years ago
- ☆405Updated 2 years ago
- Inference on CPU code for LLaMA models☆137Updated 2 years ago
- LLaMA Server combines the power of LLaMA C++ with the beauty of Chatbot UI.☆129Updated 2 years ago
- Web UI for ExLlamaV2☆510Updated 6 months ago
- AMD (Radeon GPU) ROCm based setup for popular AI tools on Ubuntu 24.04.1☆209Updated 6 months ago
- ☆158Updated last year
- Text WebUI extension to add clever Notebooks to Chat mode☆142Updated 3 weeks ago
- RWKV is a RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best …☆412Updated 2 years ago
- Landmark Attention: Random-Access Infinite Context Length for Transformers QLoRA☆124Updated 2 years ago
- Just a simple HowTo for https://github.com/johnsmith0031/alpaca_lora_4bit☆32Updated 2 years ago
- DEPRECATED!☆52Updated last year
- C++ implementation for 💫StarCoder☆456Updated last year
- Automated prompting and scoring framework to evaluate LLMs using updated human knowledge prompts☆110Updated 2 years ago
- 4 bits quantization of SantaCoder using GPTQ☆51Updated 2 years ago