Alternatives and similar repositories for llama.cpp:

Users that are interested in llama.cpp are comparing it to the libraries listed below

• catid / bitnet_cpu
  Experiments with BitNet inference on CPU
  ☆54Updated last year
• futo-org / whisper-acft
  ☆124Updated 10 months ago
• keeeeenw / TinyLlama
  The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.
  ☆11Updated last year
• mmwillet / TTS.cpp
  TTS support with GGML
  ☆32Updated this week
• pranavjad / tinyllama-bitnet
  Train your own small bitnet model
  ☆70Updated 6 months ago
• hscspring / llama.np
  Inference Llama/Llama2/Llama3 Modes in NumPy
  ☆20Updated last year
• kroggen / mamba.c
  Inference of Mamba models in pure C
  ☆188Updated last year
• casper-hansen / AutoAWQ_kernels
  ☆72Updated 5 months ago
• deepgrove-ai / Bonsai
  ☆20Updated last month
• MollySophia / rwkv-mobile
  Inference RWKV with multiple supported backends.
  ☆43Updated this week
• Ce-daros / ai-bash-response
  ☆11Updated last year
• jameswdelancey / llama3.c
  A faithful clone of Karpathy's llama2.c (one file inference, zero dependency) but fully functional with LLaMA 3 8B base and instruct mode…
  ☆126Updated 9 months ago
• iamlemec / bert.cpp
  GGML implementation of BERT model with Python bindings and quantization.
  ☆56Updated last year
• The-Swarm-Corporation / Mamba-R1
  Mamba R1 represents a novel architecture that combines the efficiency of Mamba's state space models with the scalability of Mixture of Ex…
  ☆20Updated 2 weeks ago
• RWKV / RWKV-wiki
  RWKV centralised docs for the community
  ☆24Updated last month
• ggerganov / bert.cpp
  GGML implementation of BERT model with Python bindings and quantization.
  ☆26Updated last year
• StudyingLover / ggml-tutorial
  ☆30Updated 8 months ago
• argosopentech / MetalTranslate
  Customizable machine translation in C++
  ☆51Updated last year
• cahya-wirawan / rwkv-tokenizer
  A fast RWKV Tokenizer written in Rust
  ☆45Updated last month
• MollySophia / rwkv-qualcomm
  Inference RWKV v5, v6 and v7 with Qualcomm AI Engine Direct SDK
  ☆64Updated this week
• deepshard / mixtral-8x7b-Inference
  Eh, simple and works.
  ☆27Updated last year
• FL33TW00D / coremlprofiler
  Profile your CoreML models directly from Python 🐍
  ☆27Updated 6 months ago
• wozeparrot / tinyrwkv
  tinygrad port of the RWKV large language model.
  ☆44Updated 2 months ago
• cwhy / rwkv-decon
  Trying to deconstruct RWKV in understandable terms
  ☆14Updated 2 years ago
• chu-tianxiang / QuIP-for-all
  QuIP quantization
  ☆52Updated last year
• google / minja
  A minimalistic C++ Jinja templating engine for LLM chat templates
  ☆137Updated this week
• cjpais / whisperfile
  ☆54Updated 8 months ago
• andrewkchan / deepseek.cpp
  CPU inference for the DeepSeek family of large language models in C++
  ☆291Updated this week
• marty1885 / llama.cpp
  My develoopment fork of llama.cpp. For now working on RK3588 NPU and Tenstorrent backend
  ☆91Updated 2 weeks ago
• daquexian / faster-rwkv
  ☆124Updated last year