Alternatives and similar repositories for any4

Users that are interested in any4 are comparing it to the libraries listed below

• IST-DASLab / SparseFinetuning
  Repository for Sparse Finetuning of LLMs via modified version of the MosaicML llmfoundry
  ☆42Updated last year
• IBM / triton-dejavu
  Framework to reduce autotune overhead to zero for well known deployments.
  ☆84Updated 2 weeks ago
• INT-FlashAttention2024 / INT-FlashAttention
  ☆82Updated 8 months ago
• IST-DASLab / Quartet
  ☆98Updated last month
• Qualcomm-AI-research / gptvq
  ☆35Updated last year
• meta-pytorch / superblock
  A block oriented training approach for inference time optimization.
  ☆34Updated last year
• IST-DASLab / Sparse-Marlin
  Boosting 4-bit inference kernels with 2:4 Sparsity
  ☆82Updated last year
• GindaChen / FlexFlashAttention3
  FlexAttention w/ FlashAttention3 Support
  ☆27Updated last year
• microsoft / AttentionEngine
  ☆99Updated 4 months ago
• IST-DASLab / QuEST
  Work in progress.
  ☆74Updated 3 months ago
• IST-DASLab / MicroAdam
  This repository contains code for the MicroAdam paper.
  ☆19Updated 9 months ago
• UmerHA / triton_util
  Make triton easier
  ☆47Updated last year
• stanford-futuredata / stk
  ☆113Updated last year
• IST-DASLab / QIGen
  Repository for CPU Kernel Generation for LLM Inference
  ☆26Updated 2 years ago
• TianjinYellow / StableSPAM
  ☆24Updated 6 months ago
• feifeibear / Odysseus-Transformer
  Odysseus: Playground of LLM Sequence Parallelism
  ☆77Updated last year
• Dao-AILab / grouped-latent-attention
  ☆129Updated 4 months ago
• yuzhenmao / IceFormer
  Implementation of IceFormer: Accelerated Inference with Long-Sequence Transformers on CPUs (ICLR 2024).
  ☆25Updated 2 months ago
• GATECH-EIC / ShiftAddLLM
  ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less Reparameterization
  ☆110Updated 11 months ago
• IST-DASLab / FP-Quant
  ☆42Updated last week
• feifeibear / ChituAttention
  Quantized Attention on GPU
  ☆44Updated 10 months ago
• PiotrNawrot / sparse-frontier
  The evaluation framework for training-free sparse attention in LLMs
  ☆100Updated 3 months ago
• deepspeedai / DeepSpeed-Kernels
  ☆72Updated 6 months ago
• cchan / tccl
  extensible collectives library in triton
  ☆88Updated 6 months ago
• jundaf2 / INT8-Flash-Attention-FMHA-Quantization
  ☆158Updated 2 years ago
• li-plus / flash-preference
  Accelerate LLM preference tuning via prefix sharing with a single line of code
  ☆43Updated 3 months ago
• open-lm-engine / flash-model-architectures
  A bunch of kernels that might make stuff slower 😉
  ☆59Updated this week
• tile-ai / tvm
  Open deep learning compiler stack for cpu, gpu and specialized accelerators
  ☆19Updated last week
• dame-cell / Triformer
  Transformers components but in Triton
  ☆34Updated 4 months ago
• microsoft / TileFusion
  TileFusion is an experimental C++ macro kernel template library that elevates the abstraction level in CUDA C for tile processing.
  ☆97Updated 3 months ago