Patch convolution to avoid large GPU memory usage of Conv2D
☆95Jan 23, 2025Updated last year
Alternatives and similar repositories for patch_conv
Users that are interested in patch_conv are comparing it to the libraries listed below
Sorting:
- [CVPR 2024 Highlight] DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models☆722Dec 2, 2024Updated last year
- A parallelism VAE avoids OOM for high resolution image generation☆85Aug 4, 2025Updated 6 months ago
- An auxiliary project analysis of the characteristics of KV in DiT Attention.☆33Nov 29, 2024Updated last year
- Quantized Attention on GPU☆44Nov 22, 2024Updated last year
- [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training☆259Aug 9, 2025Updated 6 months ago
- Triton-based implementation of Sparse Mixture of Experts.☆266Oct 3, 2025Updated 4 months ago
- ☆18Mar 18, 2024Updated last year
- FastCache: Fast Caching for Diffusion Transformer Through Learnable Linear Approximation [Efficient ML Model]☆46Feb 17, 2026Updated last week
- ☆190Jan 14, 2025Updated last year
- SpInfer: Leveraging Low-Level Sparsity for Efficient Large Language Model Inference on GPUs☆60Mar 25, 2025Updated 11 months ago
- ☆50Aug 21, 2025Updated 6 months ago
- [ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads☆524Feb 10, 2025Updated last year
- [ICCV 2023] Q-Diffusion: Quantizing Diffusion Models.☆370Mar 21, 2024Updated last year
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆144Dec 4, 2024Updated last year
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆816Mar 6, 2025Updated 11 months ago
- Deep Semantic Statistics Matching (D2SM) Denoising Network (ECCV22)☆25Jul 21, 2022Updated 3 years ago
- ACM Class 2017 Computer Architecture☆10Jan 11, 2018Updated 8 years ago
- [ICLR 2026 Oral] Locality-aware Parallel Decoding for Efficient Autoregressive Image Generation☆87Feb 7, 2026Updated 3 weeks ago
- PSTensor provides a way to hack the memory management of tensors in TensorFlow and PyTorch by defining your own C++ Tensor Class.☆10Feb 10, 2022Updated 4 years ago
- The official implementation of Distribution Backtracking Distillation for One-step Diffusion Models☆32Jan 25, 2025Updated last year
- Standalone commandline CLI tool for compiling Triton kernels☆20Sep 13, 2024Updated last year
- ☆11Apr 5, 2021Updated 4 years ago
- Accelerating Large-Scale Reasoning Model Inference with Sparse Self-Speculative Decoding☆93Dec 2, 2025Updated 3 months ago
- [ICLR 2024] Official code for the paper 'Elucidating the Exposure Bias in Diffusion Models'☆27May 12, 2024Updated last year
- FlexAttention w/ FlashAttention3 Support☆27Oct 5, 2024Updated last year
- Tile-Based Runtime for Ultra-Low-Latency LLM Inference☆663Feb 14, 2026Updated 2 weeks ago
- Pytorch implementation of our paper (TNNLS) -- Pruning Networks with Cross-Layer Ranking & k-Reciprocal Nearest Filters☆12Feb 24, 2022Updated 4 years ago
- ☆12Nov 5, 2024Updated last year
- A Distributed Attention Towards Linear Scalability for Ultra-Long Context, Heterogeneous Data Training☆650Updated this week
- A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit floating point (FP8 and FP4) precision on H…☆3,176Updated this week
- A collection of resources on generation.☆13Oct 9, 2022Updated 3 years ago
- Applied AI experiments and examples for PyTorch☆319Aug 22, 2025Updated 6 months ago
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.☆1,261Aug 28, 2025Updated 6 months ago
- Allow torch tensor memory to be released and resumed later☆220Feb 9, 2026Updated 3 weeks ago
- Magicube is a high-performance library for quantized sparse matrix operations (SpMM and SDDMM) of deep learning on Tensor Cores.☆91Nov 23, 2022Updated 3 years ago
- [NeurIPS 2023] ShiftAddViT: Mixture of Multiplication Primitives Towards Efficient Vision Transformer☆30Dec 6, 2023Updated 2 years ago
- Tutorials of Extending and importing TVM with CMAKE Include dependency.☆16Oct 11, 2024Updated last year
- Tile-based language built for AI computation across all scales☆138Updated this week
- A sparse attention kernel supporting mix sparse patterns☆467Jan 18, 2026Updated last month