aredden / torch-cublas-hgemm
PyTorch half precision gemm lib w/ fused optional bias + optional relu/gelu
☆64Updated 5 months ago
Alternatives and similar repositories for torch-cublas-hgemm:
Users that are interested in torch-cublas-hgemm are comparing it to the libraries listed below
- ☆68Updated 4 months ago
- [WIP] Better (FP8) attention for Hopper☆30Updated 2 months ago
- (WIP) Parallel inference for black-forest-labs' FLUX model.☆18Updated 5 months ago
- https://wavespeed.ai/ Context parallel attention that accelerates DiT model inference with dynamic caching☆264Updated this week
- ☆14Updated 5 months ago
- ☆49Updated last year
- Flux diffusion model implementation using quantized fp8 matmul & remaining layers use faster half precision accumulate, which is ~2x fast…☆264Updated 6 months ago
- Writing FLUX in Triton☆33Updated 7 months ago
- Prodigy and ScheduleFree, together at last.☆53Updated last week
- The official implementation of "CAME: Confidence-guided Adaptive Memory Optimization"☆89Updated last month
- End-to-end recipes for optimizing diffusion models with torchao and diffusers (inference and FP8 training).☆348Updated 2 months ago
- ☆104Updated 10 months ago
- 🎬 3.7× faster video generation E2E 🖼️ 1.6× faster image generation E2E ⚡ ColumnSparseAttn 9.3× vs FlashAttn‑3 💨 ColumnSparseGEMM 2.5× …☆55Updated this week
- A collection of niche / personally useful PyTorch optimizers with modified code.☆19Updated last month
- Model code for inferencing T5☆64Updated last month
- ☆125Updated 2 months ago
- faster parallel inference of mochi-1 video generation model☆119Updated 2 months ago
- Comparison of different stable diffusion implementations and optimizations☆39Updated last year
- [NeurIPS 2024] AsyncDiff: Parallelizing Diffusion Models by Asynchronous Denoising☆197Updated 2 months ago
- Accelerates Flux.1 image generation, just by using this node.☆130Updated 4 months ago
- Faster generation with text-to-image diffusion models.☆213Updated 7 months ago
- Model Compression Toolbox for Large Language Models and Diffusion Models☆462Updated last month
- A comprehensive codebase for training and finetuning Image <> Latent models.☆31Updated 2 months ago
- ☆54Updated 2 years ago
- ☆131Updated last month
- Uses DARE to merge LoRA stacks as a ComfyUI node☆32Updated 11 months ago
- Code for NeurIPS 2023 paper "Restart Sampling for Improving Generative Processes"☆149Updated last year
- Triton kernels for Flux☆20Updated 4 months ago
- ☆16Updated last year
- ComfyUI powertools for SD1.5 and SDXL model merging☆84Updated last month