Lib.rs

› Keywords #compression #vector-quantization #machine-learning #llm #vector-search

#quantization

  1. imagequant

    Convert 24/32-bit images to 8-bit palette with alpha channel. For lossy PNG compression and high-quality GIF images Dual-licensed like pngquant. See https://pngquant.org for details.

    v4.4.1 45K #palette #gif #palette-quantization #quantization #pngquant #compression

  2. ruvector-temporal-tensor

    Temporal tensor compression with tiered quantization for RuVector

    v2.0.6 2.5K #tiered #tensor #frame #compression #scale-factor #temporal #ru-vector #quantization #compressor #8-bit

  3. quantette

    Fast and high quality image quantization and palette generation

    v0.6.0 57K #color-palette #k-means #dither #palette-quantization #quantization #palette

  4. kenosis-cli

    CLI for ONNX model quantization, casting, inspection, and comparison — powered by kenosis-core

    v1.0.0 #onnx #quantization #deep-learning #ml #cli

  5. float4

    MXFP4-compatible 4-bit floating point types and block formats for Rust

    v0.2.0 55K #machine-learning #quantization #fp4 #mxfp4

  6. pngquant

    Convert 24/32-bit PNG images to efficient 8-bit format with alpha channel

    v3.0.3 650 #palette #palette-quantization #image-compression #image #quantization #compression

  7. a-sixel

    A small sixel + palette selection + dithering library

    v0.8.0 #sixel #dithering #terminal #quantization #encoding

  8. qntz

    Vector quantization primitives (RaBitQ, ternary, bit packing) for ANN systems

    v0.1.8 150 #vector-search #ann #quantization #pq #vector-quantization #compression

  9. boostr

    ML framework built on numr - attention, quantization, model architectures

    v0.1.0 #deep-learning #inference #machine-learning #transformer #quantization

  10. cubek

    CubeCL Kernels

    v0.2.0 26K #cubecl #convolution #multi-platform #quantization #matmul #attention #kernels

  11. qjl-sketch

    QJL sign-based vector compression and scoring with near-optimal distortion rate

    v0.6.0 #vector-quantization #gpu-compression #vector-compression #search #compression #gpu #quantization

  12. dithr

    Buffer-first rust dithering and halftoning library

    v0.3.0 150 #dithering #halftoning #image #graphics #quantization

  13. ternlang-compress

    LLM-to-ternary compression pipeline — quantize float models to {-1,0,+1}, build sparse zero-index, export .tern files for ternlang-ml inference

    v1.3.6 #llm #quantization #ternary #bitnet #compression

  14. lnmp-quant

    Quantization and compression for LNMP embedding vectors with minimal accuracy loss

    v0.5.16 #lnmp #embedding #vector-quantization #vector-embedding #compression #quantization #vector-compression

  15. kenosis-core

    Pure-Rust ONNX model optimization toolkit — static INT8 quantization, precision casting, and model analysis

    v1.0.0 #onnx #quantization #deep-learning #ml #optimization

  16. rabitq-rs

    Advanced vector search: RaBitQ quantization with IVF and MSTG (Multi-Scale Tree Graph) index

    v0.9.0 #vector-search #ivf #vector-quantization #ann #quantization

  17. bitnet-core

    Core BitNet implementation with fundamental data structures and algorithms

    v1.0.0 #memory-pool #performance-monitoring #neural-network #quantization

  18. bitnet-quant

    1.58-bit quantization engine for BitNet neural networks

    v1.0.0 800 #quantization #neural-network #bitnet #compression

  19. voxtral-micro

    Voxtral Micro - Minimal text-to-speech with Q4 GGUF quantization

    v1.0.0 #gguf #text-to-speech #model #voxtral #q4 #euler #gb #tts-engine #audio-buffer #quantization

  20. diskann-quantization

    DiskANN is a fast approximate nearest neighbor search library for high dimensional data

    v0.52.0 1.6K #disk-ann #quantization #nearest-neighbors-search #flat-buffers #approximate-nearest-neighbor

  21. minimum_ml

    Experimental Machine Learning Library

    v0.1.9 #machine-learning #random #logging #experimental #automatic-differentiation #quantization #neural-network #tensor-board #forward-backward #data-loader

  22. ohms-adaptq

    NOVAQ: Normalized Outlier-Vector Additive Quantization - Democratic 93-100x LLM compression with 99%+ accuracy retention. No restrictions, no gatekeeping.

    v2.0.3 650 #quantization #novaq #compression #llm

  23. bitpolar

    near-optimal vector quantization with zero training overhead — 3-bit precision, provably unbiased inner products (ICLR 2026)

    v0.3.3 #vector-search #kv-cache #vector-quantization #quantization #machine-learning #compression

  24. microcnn

    A minimal CNN framework in Rust with Quantization

    v0.1.3 #deep-learning #quantization #cnn #neural-network

  25. ruvector-fpga-transformer

    FPGA Transformer backend with deterministic latency, quantization-first design, and coherence gating

    v0.1.0 #fpga #low-latency #transformer #inference #quantization

  26. quantize-rs

    Neural network quantization toolkit for ONNX models

    v0.8.0 #onnx #neural-network #optimization #ml #quantization

  27. bitnet-quantize

    Microsoft BitNet b1.58 quantization and inference for Rust

    v0.2.1 #llm-inference #ternary #bitnet #llm #inference #quantization

  28. vq

    A vector quantization library for Rust

    v0.2.0 #vector-quantization #embedding #compression #vector-compression #quantization

  29. embedvec

    Fast, lightweight, in-process vector database with HNSW indexing, E8/H4 lattice quantization (up to 24.8x compression), metadata filtering, and PyO3 bindings

    v0.7.0 #vector-quantization #vector-database #quantization #hnsw #ann #embedding

  30. turbovec

    Fast vector quantization with 2-4 bit compression and SIMD search

    v0.2.0 #vector-search #simd #nearest-neighbor #vector-quantization #quantization #ann

  31. zeta-reticula-server

    GPU-accelerated ML inference server with Stripe billing, Hugging Face model caching, and SSE streaming

    v0.1.0 #inference #quantization #llm #ml-serving #gpu

  32. cubecl-quant

    CubeCL Quantization Library

    v0.9.0-pre.5 11K #cubecl #gpu-compute #compute-kernel #multi-platform #web-gpu #quantization #intermediate-representation #proc-macro #scientific-computing #lazy-evaluation

  33. rust-ai-core

    Unified AI engineering toolkit: orchestrates peft-rs, qlora-rs, unsloth-rs, axolotl-rs, bitnet-quantize, trit-vsa, vsa-optim-rs, and tritter-accel

    v0.3.4 #fine-tuning #quantization #machine-learning #gpu

  34. cubek-quant

    CubeK: Quantization Library

    v0.2.0 26K #cube-k #quantization #cubecl #kernel #multi-platform

  35. torsh-quantization

    Model quantization for ToRSh neural networks

    v0.1.2 #deep-learning #inference #quantization #model-compression #machine-learning

  36. axonml-quant

    Model quantization for the Axonml ML framework

    v0.6.2 #quantization #deep-learning #int8 #machine-learning #int4

  37. oxillama-quant

    Quantization kernels for all GGUF quantization types

    v0.1.2 #inference #simd #llm-inference #llm #q4 #quantization

  38. frankensearch-index

    FSVI vector index, SIMD dot product, and top-k search for frankensearch

    v0.2.0 #simd #search-index #dot-product #vector-index #top-k #vector-search #f16 #frankensearch #quantization #vector-embedding

  39. ruvector-dither

    Deterministic low-discrepancy dithering for low-bit quantization: golden-ratio and π-digit sequences for blue-noise error shaping

    v0.1.0 #inference #dither #quantization #golden-ratio #wasm

  40. sevensense-embedding

    Embedding bounded context for 7sense bioacoustics - Perch 2.0 ONNX integration

    v0.1.0 #onnx #embedding-generation #asymmetric #perch #integration #gpu #similarity-search #quantization #batch-processing #audio

  41. amv_decoder

    Experimental AMV parser and decoder for KiriKiri2 / KiriKiriZ engine videos

    v0.1.0 #video-decoder #reverse-engineering #experimental #packet #file-header #game-engine #rgba #endianness #ppm #quantization

  42. imagequant-sys

    Convert 24/32-bit images to 8-bit palette with alpha channel. C API/FFI libimagequant that powers pngquant lossy PNG compressor. Dual-licensed like pngquant. See https://pngquant.org for details.

    v4.1.0 500 #palette #image #palette-quantization #quantization #quant #dither

  43. turbo-vec

    TurboQuant-based vector quantization and search library

    v0.1.0 #simd #vector-quantization #quantization #search #ann

  44. turbo-quant

    TurboQuant, PolarQuant, and QJL — zero-overhead vector quantization for semantic search and KV cache compression (ICLR 2026)

    v0.1.0 #vector-quantization #compression #quantization #vector-search #embedding #machine-learning #vector-compression

  45. kizzasi-tokenizer

    Signal quantization and tokenization for Kizzasi AGSP - VQ-VAE, μ-law, continuous embeddings

    v0.2.1 #audio #quantization #vq-vae #compression

  46. whisperforge-core

    GPU-accelerated Whisper model inference with streaming audio, quantization, and KV-cached decoding

    v0.3.1 #whisper #text-to-speech #quantization #burn #gpu

  47. gollum-compute

    Machine Learning and other Compute related support for Gollum

    v0.4.0 #machine-learning #inference #gollum #ternary #model #fine-tuning #quantization

  48. oxicuda-quant

    GPU-accelerated quantization and model compression engine for OxiCUDA

    v0.1.6 #quantization #compression #gpu-compression #deep-learning

  49. ruvector-rabitq

    RaBitQ: rotation-based 1-bit quantization for ultra-fast approximate nearest-neighbor search with theoretical error bounds

    v2.2.0 #nearest-neighbors-search #asymmetric #approximate-knn #rabitq #1-bit #quantization #rerank #top-k #max-heap #logging

  50. rotorvec

    Vector index using Clifford-rotor block-diagonal quantization (RotorQuant)

    v0.2.1 #rotor #quantization #vector-search #ann #clifford #vector-quantization

  51. oxify-vector

    In-memory vector search and similarity operations for OxiFY (ported from OxiRS)

    v0.1.0 #vector-search #similarity-search #hnsw #vector-similarity #simd #vector-quantization #quantization

  52. kwaai-compression

    Compression utilities for KwaaiNet - 8-bit quantization, gradient compression

    v0.4.63 #gradients #quantization #bandwidth #compression #optimization

  53. cp-compress

    DCT-based embedding compression for Canon Protocol (CP-016)

    v0.3.1 #compression #canon #protocols #dct #embedding #cosine-similarity #8-bit #quantization

  54. aitna

    A local LLM inference platform with model pulling, quantization optimization, and high-performance serving

    v0.1.0-alpha #inference #quantization #llm #llm-inference #local

  55. pixelization

    An image quantization and pixelization library implementing K-Means and PIA (Pixelated Image Abstraction)

    v0.1.1 #k-means #quantization #pia #pixelize

  56. haagenti-mobile

    Mobile deployment support for iOS (CoreML) and Android (NNAPI)

    v0.1.0 #quantization #coreml #inference #nnapi #mobile

  57. haagenti-adaptive

    Adaptive precision scheduling for diffusion inference

    v0.1.0 #inference #quantization #precision #adaptive

  58. rvf-quant

    RuVector Format temperature-tiered vector quantization (f32/f16/u8/binary)

    v0.1.0 #vector-quantization #rvf #quantization #embedding #compression

  59. rscolorq

    Spatial color quantization, a Rust port of scolorq

    v0.2.0 #palette-quantization #graphics #spatial #quantization #halftone #palette

  60. zeta-quantization

    Advanced quantization engine for efficient LLM inference

    v0.1.0 #quantization #llm-inference #optimization #llm #inference #compression

  61. polarquant

    Walsh-Hadamard rotation + polar coordinate quantization for LLM weight and KV cache compression

    v0.1.0 #llm #compression #polar #hadamard #quantization

  62. vector_quantizer

    vector quantization utilities and functions

    v0.0.3 160 #vector-quantization #product-quantization #embedding #quantization

  63. numquant

    Quantize numbers to a smaller range to save bandwidth or memory data types and back again

    v0.2.0 1.8K #numeric #quantization

  64. greenfield

    images

    v0.1.4 #image #64-bit #image-width #color #endian #quantization #serialization #color-quantization #16-bit

  65. hanzo-llm

    Hanzo AI - Llm Library

    v1.1.11 #llm #artificial-intelligence #model-selection #routing #hamiltonian #price #quantization #regime #hidden-markov-model #hanzo

  66. exoquant

    Very high quality image quantization

    v0.2.0 1.0K #palette-quantization #palette #quantization

    67. Try searching with DuckDuckGo.

  67. palette_extract

    port of Leptonica's modified media cut quantization algorithm

    v0.1.0 130 #color-palette #palette-quantization #image #color-quantization #mmcq #quantization

  68. haagenti-neural

    Neural compression using learned codebooks for 10x model compression

    v0.1.0 #codebook #compression #quantization #neural

  69. numcodecs-linear-quantize

    Linear Quantization codec implementation for the numcodecs API

    v0.5.0 #numcodecs #linear #quantization

  70. whisper-cpp-plus-sys

    Low-level FFI bindings for whisper.cpp

    v0.1.4 120 #whisper-cpp #cuda #open-blas #quantization #metal #bindings-for-whisper

  71. mnemonist-quant

    TurboQuant vector quantization for mnemonist — near-optimal MSE and inner-product quantizers

    v0.4.3 #vector-quantization #quantization #embedding #turboquant #vector-compression

  72. vil_quantized

    D13 - Model Quantization Runtime for VIL

    v0.4.0 #gguf #vil #quantization #model #quantized #distributed-systems #model-loading #candle #ggml #zero-copy

  73. quantized-pathfinding

    Quantization before pathfinding

    v0.1.1 #path-finding #quantization #quantized-astar #picking

  74. rabitq

    vector search algorithm

    v0.2.2 320 #vector-search #quantization #binary-dot-product

  75. ashares

    中国股市A股股票行情实时数据最简封装API接口,包含日线,分时分钟线,以及均线数据,可用来研究，量化分析，证券股票程序化自动化交易系统。目前提供新浪腾讯接口，…

    v0.1.0 #quantization #etf #stock

  76. ctp-sys

    ctp rust binding

    v0.1.3 #stock #quantization #future

  77. aprender-quant

    K-quantization formats (Q4_K, Q5_K, Q6_K) for GGUF/APR model weights

    v0.31.2 850 #gguf #quantization #llm #neural-network #machine-learning

  78. iris-lib

    that creates color palettes from images using the median cut algorithm

    v0.1.0 #color #quantization #image #color-quantization #cli

  79. cliris

    A cli tool that creates color palettes from images using the median cut algorithm

    v0.2.0 #image #quantization #color #color-quantization

  80. csc411_arith

    Quantization of floating-point chroma values for URI CSC 411

    v0.1.0 #chroma #quantization #value #floating-point #csc #411

  81. qshare

    量化数据：股票、期货等

    v0.1.4 #stock #quantization #future

  82. mcq

    port of Java implementation of Median Cut Quantization algorithm

    v0.1.0 #graphics #quantization #color #median #color-matching

  83. ggml

    Semi-idiomatic Rust bindings for the ggml library (from ggml-sys)

    v0.1.1 370 #language-model #llm #bindings #version #vocabulary #quantization #version-number #machine-learning #component-model #artificial-intelligence

  84. color-theme

    A CLI tool to extract a colour 'palette' and theme color from an image

    v0.1.0 #image #graphics #quantization #palette-quantization #color-palette #palette #color-image

  85. entrenar-inspect

    SafeTensors model inspection and format conversion

    v0.1.0 #gguf #model-format #format-conversion #entrenar #inspection #safe-tensors #apr #quantization #aprender

  86. image-reducer

    Reduce image size by quantization

    v0.1.1 #image-size #tiny-png #size-optimization #multi-threading #reduce #quantization #database