Alternatives and similar repositories for ggml-python:

Users that are interested in ggml-python are comparing it to the libraries listed below

• astramind-ai / BitMat
  An efficent implementation of the method proposed in "The Era of 1-bit LLMs"
  ☆154Updated 3 months ago
• kroggen / mamba.c
  Inference of Mamba models in pure C
  ☆183Updated 10 months ago
• staghado / vit.cpp
  Inference Vision Transformer (ViT) in plain C/C++ with ggml
  ☆244Updated 9 months ago
• Cornell-RelaxML / QuIP
  Code for paper: "QuIP: 2-Bit Quantization of Large Language Models With Guarantees"
  ☆358Updated 10 months ago
• Cornell-RelaxML / quip-sharp
  ☆515Updated 2 months ago
• IST-DASLab / qmoe
  Code for the paper "QMoE: Practical Sub-1-Bit Compression of Trillion-Parameter Models".
  ☆263Updated last year
• rafacelente / bllama
  1.58-bit LLaMa model
  ☆80Updated 9 months ago
• fpgaminer / GPTQ-triton
  GPTQ inference Triton kernel
  ☆291Updated last year
• ggml-org / p1
  LLM-based code completion engine
  ☆178Updated last month
• apple / ml-recurrent-drafter
  ☆190Updated last month
• huggingface / optimum-tpu
  Google TPU optimizations for transformers models
  ☆86Updated this week
• neuralmagic / nm-vllm
  A high-throughput and memory-efficient inference and serving engine for LLMs
  ☆257Updated 3 months ago
• monatis / clip.cpp
  CLIP inference in plain C/C++ with no extra dependencies
  ☆474Updated 5 months ago
• HazyResearch / lolcats
  Repo for "LoLCATs: On Low-Rank Linearizing of Large Language Models"
  ☆203Updated 3 weeks ago
• thomasgauthier / LoRD
  Low-Rank adapter extraction for fine-tuned transformers models
  ☆165Updated 8 months ago
• intel / neural-speed
  An innovative library for efficient LLM inference via low-bit quantization
  ☆352Updated 4 months ago
• philipturner / metal-flash-attention
  FlashAttention (Metal Port)
  ☆425Updated 3 months ago
• NolanoOrg / cformers
  SoTA Transformers with C-backend for fast inference on your CPU.
  ☆312Updated last year
• keeeeenw / MicroLlama
  Micro Llama is a small Llama based model with 300M parameters trained from scratch with $500 budget
  ☆141Updated 9 months ago
• wejoncy / QLLM
  A general 2-8 bits quantization toolbox with GPTQ/AWQ/HQQ, and export to onnx/onnx-runtime easily.
  ☆153Updated 3 months ago
• trzy / llava-cpp-server
  LLaVA server (llama.cpp).
  ☆176Updated last year
• thomasantony / llamacpp-python
  Python bindings for llama.cpp
  ☆199Updated last year
• cognitivecomputations / laserRMT
  This is our own implementation of 'Layer Selective Rank Reduction'
  ☆232Updated 7 months ago
• kayvr / token-hawk
  WebGPU LLM inference tuned by hand
  ☆148Updated last year
• sdan / selfextend
  an implementation of Self-Extend, to expand the context window via grouped attention
  ☆118Updated last year
• mobiusml / hqq
  Official implementation of Half-Quadratic Quantization (HQQ)
  ☆733Updated this week
• chu-tianxiang / llama-cpp-torch
  llama.cpp to PyTorch Converter
  ☆27Updated 9 months ago
• OpenGVLab / EfficientQAT
  EfficientQAT: Efficient Quantization-Aware Training for Large Language Models
  ☆237Updated 3 months ago
• ikawrakow / ik_llama.cpp
  llama.cpp fork with additional SOTA quants and improved performance
  ☆126Updated this week
• VITA-Group / Q-GaLore
  Q-GaLore: Quantized GaLore with INT4 Projection and Layer-Adaptive Low-Rank Gradients.
  ☆188Updated 6 months ago