Alternatives and similar repositories for FP-Quant

Users that are interested in FP-Quant are comparing it to the libraries listed below

• IST-DASLab / qutlass
  QuTLASS: CUTLASS-Powered Quantized BLAS for Deep Learning
  ☆120Updated last week
• INT-FlashAttention2024 / INT-FlashAttention
  ☆83Updated 9 months ago
• tgale96 / grouped_gemm
  PyTorch bindings for CUTLASS grouped GEMM.
  ☆125Updated 5 months ago
• thu-ml / Jetfire-INT8Training
  ☆58Updated last year
• flashinfer-ai / cutlass-viz
  ☆64Updated 6 months ago
• Qualcomm-AI-research / gptvq
  ☆36Updated last year
• PipeFusion / PipeFusion
  A Suite for Parallel Inference of Diffusion Transformers (DiTs) on multi-GPU Clusters
  ☆52Updated last year
• wangsiping97 / FastGEMV
  High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.
  ☆120Updated last year
• feifeibear / ChituAttention
  Quantized Attention on GPU
  ☆44Updated 11 months ago
• ankan-ban / llama_cu_awq
  llama INT4 cuda inference with AWQ
  ☆55Updated 9 months ago
• aiha-lab / MX-QLLM
  LLM Inference with Microscaling Format
  ☆31Updated 11 months ago
• Dao-AILab / fast-hadamard-transform
  Fast Hadamard transform in CUDA, with a PyTorch interface
  ☆255Updated 2 weeks ago
• HandH1998 / QQQ
  QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.
  ☆145Updated 2 months ago
• DD-DuDa / BitLadder
  A GPU-optimized system for efficient long-context LLMs decoding with low-bit KV cache.
  ☆61Updated 2 weeks ago
• feifeibear / Odysseus-Transformer
  Odysseus: Playground of LLM Sequence Parallelism
  ☆78Updated last year
• IST-DASLab / Sparse-Marlin
  Boosting 4-bit inference kernels with 2:4 Sparsity
  ☆85Updated last year
• usyd-fsalab / fp6_llm
  An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).
  ☆268Updated 3 months ago
• microsoft / SparTA
  ☆154Updated last year
• IBM / triton-dejavu
  Framework to reduce autotune overhead to zero for well known deployments.
  ☆84Updated last month
• microsoft / TileFusion
  TileFusion is an experimental C++ macro kernel template library that elevates the abstraction level in CUDA C for tile processing.
  ☆100Updated 4 months ago
• NVlabs / COAT
  [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training
  ☆243Updated 2 months ago
• tile-ai / AttentionEngine
  ☆50Updated 5 months ago
• ademeure / DeeperGEMM
  DeeperGEMM: crazy optimized version
  ☆72Updated 5 months ago
• FasterDecoding / TEAL
  ☆145Updated 8 months ago
• IST-DASLab / HALO
  HALO: Hadamard-Assisted Low-Precision Optimization and Training method for finetuning LLMs. 🚀 The official implementation of https://arx…
  ☆28Updated 8 months ago
• Dao-AILab / grouped-latent-attention
  ☆130Updated 5 months ago
• andy-yang-1 / DoubleSparse
  16-fold memory access reduction with nearly no loss
  ☆104Updated 7 months ago
• ChenMnZ / PrefixQuant
  An algorithm for weight-activation quantization (W4A4, W4A8) of LLMs, supporting both static and dynamic quantization
  ☆161Updated this week
• triton-lang / kernels
  ☆93Updated 11 months ago
• microsoft / AttentionEngine
  ☆102Updated 5 months ago