Alternatives and similar repositories for metal-flash-attention

Users that are interested in metal-flash-attention are comparing it to the libraries listed below

• ml-explore / mlx-data
  Efficient framework-agnostic data loading
  ☆455Updated 3 months ago
• Cornell-RelaxML / quip-sharp
  ☆576Updated last year
• apple / ml-recurrent-drafter
  ☆219Updated 11 months ago
• TristanBilot / mlx-benchmark
  Benchmark of Apple MLX operations on all Apple Silicon chips (GPU, CPU) + MPS and CUDA.
  ☆209Updated last week
• riccardomusmeci / mlx-llm
  Large Language Models (LLMs) applications and tools running on Apple Silicon in real-time with Apple MLX.
  ☆459Updated 11 months ago
• exo-explore / mlx-bitnet
  1.58 Bit LLM on Apple Silicon using MLX
  ☆237Updated last year
• abetlen / ggml-python
  Python bindings for ggml
  ☆146Updated last year
• smpanaro / coreml-llm-cli
  CLI to demonstrate running a large language model (LLM) on Apple Neural Engine.
  ☆117Updated last year
• smpanaro / more-ane-transformers
  Run transformers (incl. LLMs) on the Apple Neural Engine.
  ☆63Updated 2 years ago
• willccbb / mlx_parallm
  Fast parallel LLM inference for MLX
  ☆241Updated last year
• ml-explore / mlx-c
  C API for MLX
  ☆158Updated this week
• dropbox / hqq
  Official implementation of Half-Quadratic Quantization (HQQ)
  ☆905Updated 3 weeks ago
• argmaxinc / DiffusionKit
  On-device Image Generation for Apple Silicon
  ☆683Updated 9 months ago
• regrettable-username / llm.metal
  LLM training in simple, raw C/Metal Shading Language
  ☆60Updated last year
• IST-DASLab / qmoe
  Code for the paper "QMoE: Practical Sub-1-Bit Compression of Trillion-Parameter Models".
  ☆279Updated 2 years ago
• ggml-org / p1
  LLM-based code completion engine
  ☆190Updated 11 months ago
• Cornell-RelaxML / QuIP
  Code for paper: "QuIP: 2-Bit Quantization of Large Language Models With Guarantees"
  ☆393Updated last year
• smpanaro / ModernBERT-AppleNeuralEngine
  ModernBERT model optimized for Apple Neural Engine.
  ☆29Updated last year
• kroggen / mamba.c
  Inference of Mamba models in pure C
  ☆196Updated last year
• kasper0406 / stablehlo-coreml
  Convert StableHLO models into Apple Core ML format
  ☆21Updated 3 weeks ago
• JosefAlbers / Phi-3-Vision-MLX
  Phi-3.5 for Mac: Locally-run Vision and Language Models for Apple Silicon
  ☆274Updated 2 months ago
• RobertRiachi / ANE-Optimized-Whisper-OpenAI
  ☆58Updated 2 years ago
• microsoft / VPTQ
  VPTQ, A Flexible and Extreme low-bit quantization algorithm
  ☆671Updated 8 months ago
• Infini-AI-Lab / Sequoia
  scalable and robust tree-based speculative decoding algorithm
  ☆366Updated 11 months ago
• dropbox / gemlite
  Fast low-bit matmul kernels in Triton
  ☆418Updated 3 weeks ago
• philipturner / metal-benchmarks
  Apple GPU microarchitecture
  ☆571Updated last year
• arcee-ai / fastmlx
  FastMLX is a high performance production ready API to host MLX models.
  ☆339Updated 9 months ago
• astramind-ai / BitMat
  An efficent implementation of the method proposed in "The Era of 1-bit LLMs"
  ☆155Updated last year
• BobMcDear / attorch
  A subset of PyTorch's neural network modules, written in Python using OpenAI's Triton.
  ☆592Updated 5 months ago
• FL33TW00D / coremlprofiler
  Profile your CoreML models directly from Python 🐍
  ☆29Updated 4 months ago