aredden / torch-cublas-hgemmLinks
PyTorch half precision gemm lib w/ fused optional bias + optional relu/gelu
☆66Updated 6 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
Sorting:
- [WIP] Better (FP8) attention for Hopper☆30Updated 3 months ago
- ☆70Updated 5 months ago
- ☆14Updated 6 months ago
- (WIP) Parallel inference for black-forest-labs' FLUX model.☆19Updated 6 months ago
- https://wavespeed.ai/ Context parallel attention that accelerates DiT model inference with dynamic caching☆290Updated 3 weeks ago
- ☆49Updated last year
- 🎬 3.7× faster video generation E2E 🖼️ 1.6× faster image generation E2E ⚡ ColumnSparseAttn 9.3× vs FlashAttn‑3 💨 ColumnSparseGEMM 2.5× …☆65Updated this week
- Writing FLUX in Triton☆33Updated 8 months ago
- Light Video Generation Inference Framework☆35Updated last week
- The official implementation of "CAME: Confidence-guided Adaptive Memory Optimization"☆90Updated 2 months ago
- Prodigy and Schedule-Free, together at last.☆56Updated this week
- Accelerates Flux.1 image generation, just by using this node.☆132Updated 5 months ago
- Flux diffusion model implementation using quantized fp8 matmul & remaining layers use faster half precision accumulate, which is ~2x fast…☆266Updated 7 months ago
- ☆125Updated 3 months ago
- ☆17Updated last year
- End-to-end recipes for optimizing diffusion models with torchao and diffusers (inference and FP8 training).☆358Updated last week
- Model Compression Toolbox for Large Language Models and Diffusion Models☆489Updated 2 months ago
- Uses DARE to merge LoRA stacks as a ComfyUI node☆33Updated last year
- faster parallel inference of mochi-1 video generation model☆121Updated 3 months ago
- A comprehensive codebase for training and finetuning Image <> Latent models.☆35Updated 3 months ago
- Model code for inferencing T5☆65Updated 2 months ago
- ComfyUI powertools for SD1.5 and SDXL model merging☆86Updated 2 months ago
- Merge safetensor files using the technique described in "Language Models are Super Mario: Absorbing Abilities from Homologous Models as a…☆79Updated 7 months ago
- [NeurIPS 2024] AsyncDiff: Parallelizing Diffusion Models by Asynchronous Denoising☆203Updated 3 months ago
- [ICML2025] LoRA fine-tune directly on the quantized models.☆28Updated 6 months ago
- QuIP quantization☆52Updated last year
- Unofficial extension implementation of CausVid☆25Updated last month
- Triton kernels for Flux☆20Updated 5 months ago
- Faster Pytorch bitsandbytes 4bit fp4 nn.Linear ops☆28Updated last year
- ☆97Updated last month