Alternatives and similar repositories for candle-paged-attention

Users that are interested in candle-paged-attention are comparing it to the libraries listed below

• LaurentMazare / glim
  ☆19Updated last year
• chenwanqq / candle-llava
  implement llava using candle
  ☆15Updated last year
• KGrewal1 / candle-optimisers
  A collection of optimisers for use with candle
  ☆44Updated this week
• LaurentMazare / tch-ext
  Sample Python extension using Rust/PyO3/tch to interact with PyTorch
  ☆39Updated last year
• kuterd / opal_ptx
  Experimental GPU language with meta-programming
  ☆24Updated last year
• EricLBuehler / safetensors_explorer
  CLI utility to inspect and explore .safetensors and .gguf files
  ☆35Updated last month
• kyutai-labs / kaudio
  Rust crate for some audio utilities
  ☆25Updated 9 months ago
• LaurentMazare / tboard-rs
  Read and write tensorboard data using Rust
  ☆24Updated last year
• lianakoleva / no-libtorch-compile
  ☆21Updated 9 months ago
• LaurentMazare / mamba.rs
  ☆135Updated last year
• michaelfeil / candle-flash-attn-v3
  ☆13Updated 10 months ago
• EricLBuehler / candle_graphs
  Graph model execution API for Candle
  ☆16Updated 4 months ago
• LaurentMazare / gemm-metal
  ☆17Updated last year
• FL33TW00D / steelix
  Your one stop CLI for ONNX model analysis.
  ☆47Updated 3 years ago
• LaurentMazare / ug
  Experimental compiler for deep learning models
  ☆71Updated 2 months ago
• Narsil / bindgen_cuda
  ☆26Updated 7 months ago
• fal-ai-community / NativeSparseAttention
  research impl of Native Sparse Attention (2502.11089)
  ☆63Updated 9 months ago
• Chillee / lit-llama
  Simple (fast) transformer inference in PyTorch with torch.compile + lit-llama code
  ☆10Updated 2 years ago
• huggingface / kernel-builder
  👷 Build compute kernels
  ☆192Updated this week
• cchan / tccl
  extensible collectives library in triton
  ☆91Updated 8 months ago
• srush / triton-autodiff
  Experiment of using Tangent to autodiff triton
  ☆80Updated last year
• huggingface / pyo3-special-method-derive
  Automatically derive Python dunder methods for your Rust code
  ☆20Updated 7 months ago
• thecharlieblake / lovely-llama
  An implementation of the Llama architecture, to instruct and delight
  ☆21Updated 6 months ago
• sarah-quinones / gemm
  ☆96Updated 3 weeks ago
• facebookresearch / fastgen
  Simple high-throughput inference library
  ☆150Updated 6 months ago
• eugenehp / gpu-fft
  GPU based FFT written in Rust and CubeCL
  ☆24Updated 5 months ago
• Dan-wanna-M / kbnf
  A high-performance constrained decoding engine based on context free grammar in Rust
  ☆56Updated 6 months ago
• open-lm-engine / accelerated-model-architectures
  A bunch of kernels that might make stuff slower 😉
  ☆65Updated last week
• EricLBuehler / float8
  8-bit floating point types for Rust
  ☆61Updated last week
• EricLBuehler / candle-lora
  Low rank adaptation (LoRA) for Candle.
  ☆168Updated 7 months ago