Alternatives and similar repositories for q8_kernels

Users that are interested in q8_kernels are comparing it to the libraries listed below

• chengzeyi / piflux
  (WIP) Parallel inference for black-forest-labs' FLUX model.
  ☆18Updated last year
• WaveSpeedAI / QuantumAttention
  [WIP] Better (FP8) attention for Hopper
  ☆32Updated 8 months ago
• sandyresearch / chipmunk
  🎬 3.7× faster video generation E2E 🖼️ 1.6× faster image generation E2E ⚡ ColumnSparseAttn 9.3× vs FlashAttn‑3 💨 ColumnSparseGEMM 2.5× …
  ☆90Updated 2 months ago
• huggingface / flux-fast
  Making Flux go brrr on GPUs.
  ☆154Updated 4 months ago
• aredden / torch-cublas-hgemm
  PyTorch half precision gemm lib w/ fused optional bias + optional relu/gelu
  ☆76Updated 11 months ago
• timudk / flux_triton
  Writing FLUX in Triton
  ☆41Updated last year
• mit-han-lab / patch_conv
  Patch convolution to avoid large GPU memory usage of Conv2D
  ☆93Updated 9 months ago
• xdit-project / DistVAE
  A parallelism VAE avoids OOM for high resolution image generation
  ☆82Updated 3 months ago
• microsoft / AttentionEngine
  ☆109Updated 6 months ago
• hao-ai-lab / Awesome-Video-Attention
  A curated list of recent papers on efficient video attention for video diffusion models, including sparsification, quantization, and cach…
  ☆47Updated 3 weeks ago
• Cornell-RelaxML / qtip
  ☆154Updated 4 months ago
• PipeFusion / PipeFusion
  A Suite for Parallel Inference of Diffusion Transformers (DiTs) on multi-GPU Clusters
  ☆52Updated last year
• chengzeyi / ParaAttention
  https://wavespeed.ai/ Context parallel attention that accelerates DiT model inference with dynamic caching
  ☆388Updated 4 months ago
• togethercomputer / flash-attention-3
  Fast and memory-efficient exact attention
  ☆23Updated 11 months ago
• IST-DASLab / Quartet
  ☆106Updated 2 weeks ago
• xdit-project / DiTCacheAnalysis
  An auxiliary project analysis of the characteristics of KV in DiT Attention.
  ☆32Updated 11 months ago
• xdit-project / mochi-xdit
  faster parallel inference of mochi-1 video generation model
  ☆125Updated 8 months ago
• gpu-mode / ring-attention
  ring-attention experiments
  ☆155Updated last year
• IST-DASLab / qutlass
  QuTLASS: CUTLASS-Powered Quantized BLAS for Deep Learning
  ☆134Updated last week
• vllm-project / compressed-tensors
  A safetensors extension to efficiently store sparse quantized tensors on disk
  ☆204Updated last week
• RiseAI-Sys / DAX
  High performance inference engine for diffusion models
  ☆95Updated 2 months ago
• vipshop / cache-dit
  A Unified and Flexible Inference Engine with Hybrid Cache Acceleration and Parallelism for 🤗DiTs.
  ☆560Updated this week
• meta-pytorch / float8_experimental
  This repository contains the experimental PyTorch native float8 training UX
  ☆223Updated last year
• thu-nics / MixDQ
  [ECCV24] MixDQ: Memory-Efficient Few-Step Text-to-Image Diffusion Models with Metric-Decoupled Mixed Precision Quantization
  ☆46Updated 11 months ago
• thu-nics / DiTFastAttn
  ☆186Updated 10 months ago
• ByteDance-Seed / cudaLLM
  ☆121Updated 3 months ago
• tridao / flash-attention-wheels
  ☆57Updated last year
• thu-ml / SLA
  SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable Sparse–Linear Attention
  ☆137Updated last week
• sayakpaul / diffusers-torchao
  End-to-end recipes for optimizing diffusion models with torchao and diffusers (inference and FP8 training).
  ☆383Updated 5 months ago
• fal-ai / flashpack
  High-throughput tensor loading for PyTorch
  ☆197Updated this week