olealgoritme / gddr6

Related projects: ⓘ

• xor2k / gpu_undervolt
  ☆41Updated last year
• jllllll / exllama
  A more memory-efficient rewrite of the HF transformers implementation of Llama for use with quantized weights.
  ☆66Updated 11 months ago
• arlo-phoenix / bitsandbytes-rocm-5.6
  8-bit CUDA functions for PyTorch Rocm compatible
  ☆37Updated 5 months ago
• ROCm / AITemplate
  AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (N…
  ☆11Updated 2 months ago
• ROCm / flash-attention
  Fast and memory-efficient exact attention
  ☆126Updated this week
• broncotc / bitsandbytes-rocm
  ☆37Updated last year
• euclaise / supertrainer2000
  ☆48Updated 6 months ago
• ROCm / bitsandbytes
  8-bit CUDA functions for PyTorch
  ☆34Updated this week
• chu-tianxiang / llama-cpp-torch
  llama.cpp to PyTorch Converter
  ☆21Updated 5 months ago
• xuhuisheng / rocm-build
  build scripts for ROCm
  ☆181Updated 8 months ago
• AlpinDale / RPTQ-for-LLaMA
  Efficient 3bit/4bit quantization of LLaMA models
  ☆19Updated last year
• astramind-ai / BitMat
  An efficent implementation of the method proposed in "The Era of 1-bit LLMs"
  ☆155Updated 2 months ago
• amd / fuzzyHSA
  ☆51Updated 3 months ago
• abetlen / ggml-python
  Python bindings for ggml
  ☆125Updated 2 weeks ago
• chu-tianxiang / QuIP-for-all
  QuIP quantization
  ☆41Updated 6 months ago
• pomoke / torch-apu-helper
  Make PyTorch models at least run on APUs.
  ☆41Updated 9 months ago
• AlpinDale / sparsegpt-for-LLaMA
  Code for the paper "SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot" with LLaMA implementation.
  ☆68Updated last year
• eugenepentland / landmark-attention-qlora
  Landmark Attention: Random-Access Infinite Context Length for Transformers QLoRA
  ☆123Updated last year
• lucidrains / grokfast-pytorch
  Explorations into the proposal from the paper "Grokfast, Accelerated Grokking by Amplifying Slow Gradients"
  ☆82Updated 3 weeks ago
• EmbeddedLLM / vllm-rocm
  vLLM: A high-throughput and memory-efficient inference and serving engine for LLMs
  ☆87Updated this week
• kalomaze / koboldcpp
  My personal fork of koboldcpp where I hack in experimental samplers.
  ☆42Updated 4 months ago
• Gryphe / MergeMonster
  An unsupervised model merging algorithm for Transformers-based language models.
  ☆96Updated 4 months ago
• agrocylo / bitsandbytes-rocm
  8-bit CUDA functions for PyTorch, ported to HIP for use in AMD GPUs
  ☆43Updated last year
• AlpinDale / gptslop
  A community list of common phrases generated by GPT and Claude models
  ☆68Updated 10 months ago
• marty1885 / llama.cpp
  My develoopment fork of llama.cpp. For now working on RK3588 NPU and Tenstorrent backend
  ☆62Updated last week
• Cippo95 / nvidia-fan-control
  Controlling fans on my NVIDIA graphics card
  ☆19Updated 2 months ago
• aredden / torch-cublas-hgemm
  PyTorch half precision gemm lib w/ fused optional bias + optional relu/gelu
  ☆25Updated 3 weeks ago
• zarakiquemparte / zaraki-tools
  ☆26Updated last year
• crowsonkb / consistency-models
  A JAX implementation of the continuous time formulation of Consistency Models
  ☆83Updated last year
• srush / triton-autodiff
  Experiment of using Tangent to autodiff triton
  ☆66Updated 7 months ago