fal-ai / flashpackLinks
High-throughput tensor loading for PyTorch
☆213Updated 3 weeks ago
Alternatives and similar repositories for flashpack
Users that are interested in flashpack are comparing it to the libraries listed below
Sorting:
- Making Flux go brrr on GPUs.☆158Updated 5 months ago
- faster parallel inference of mochi-1 video generation model☆126Updated 10 months ago
- [WIP] Better (FP8) attention for Hopper☆32Updated 10 months ago
- Recaption large (Web)Datasets with vllm and save the artifacts.☆52Updated last year
- ☆24Updated last year
- PyTorch half precision gemm lib w/ fused optional bias + optional relu/gelu☆75Updated last year
- ☆170Updated last month
- Focused on fast experimentation and simplicity☆76Updated last year
- ☆48Updated 10 months ago
- End-to-end recipes for optimizing diffusion models with torchao and diffusers (inference and FP8 training).☆388Updated 6 months ago
- ☆28Updated 2 months ago
- Writing FLUX in Triton☆41Updated last year
- Comparison of different stable diffusion implementations and optimizations☆40Updated last year
- Model code for inferencing T5☆66Updated 9 months ago
- Flux diffusion model implementation using quantized fp8 matmul & remaining layers use faster half precision accumulate, which is ~2x fast…☆285Updated last year
- RAM is all you need☆256Updated last month
- Lightweight package that tracks and summarizes code changes using LLMs (Large Language Models)☆34Updated 10 months ago
- Fast and memory-efficient exact attention☆24Updated last year
- https://hf.co/hexgrad/Kokoro-82M☆14Updated 10 months ago
- This repository provides a minimal, single-file implementation of SingLoRA (Single Matrix Low-Rank Adaptation) as described in the paper …☆44Updated last week
- ☆78Updated last year
- Community ComfyUI workflows running on fal.ai☆57Updated last year
- (CVPR 2025) Switti: Designing Scale-Wise Transformers for Text-to-Image Synthesis☆200Updated 5 months ago
- A pipeline parallel training script for LLMs.☆164Updated 7 months ago
- ☆30Updated last year
- ☆69Updated last year
- ☆164Updated last week
- (WIP) Parallel inference for black-forest-labs' FLUX model.☆18Updated last year
- ☆27Updated last year
- Text-to-video generation: CogVideoX (2024) and CogVideo (ICLR 2023)☆17Updated last year