Gradually-Warmup Learning Rate Scheduler for PyTorch
-
Updated
Oct 10, 2024 - Python
#
pytorch-extension
Here are 24 public repositories matching this topic...
Spatial Attentive Single-Image Deraining with a High Quality Real Rain Dataset (CVPR'19)
-
Updated
Aug 30, 2021 - Jupyter Notebook
Polynomial Learning Rate Decay Scheduler for PyTorch
-
Updated
Dec 25, 2021 - Python
A pyTorch Extension for Applied Mathematics
-
Updated
Mar 17, 2020 - Python
Faster Pytorch bitsandbytes 4bit fp4 nn.Linear ops
-
Updated
Mar 16, 2024 - Python
Minimal FlashAttention in CUDA C++/CuTe: readable WMMA/CuTe kernels, no NxN workspace, up to 4.5x faster than naive PyTorch
cuda attention cutlass cute gpu-kernels pytorch-extension tensor-cores llm flash-attention flashattention wmma
-
Updated
Jun 2, 2026 - Cuda
Pytorch extension for openml-python
-
Updated
Jun 15, 2026 - Jupyter Notebook
Template for CUDA / C++ extension writing with PyTorch
-
Updated
Sep 9, 2020 - Python
XNOR-Net with binary conv2d kernels with XNOR GEMM op, support both CPU and GPU.
cpp cuda pytorch xnor-net gemm binary-convolutions xnor-convolutions binary-neural-networks binary-op pytorch-extension
-
Updated
Oct 25, 2022 - C
A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch
-
Updated
Sep 11, 2021 - Python
A humble exploratory PoC for a hardware-native, optical timing-frozen control plane engine. Fuses inline CUDA PTX, RAII memory tunnels, and 4D JAX shard_map structures to investigate 0ns-overhead fault-tolerant routing for hyperscale distributed AI.
distributed-systems fault-tolerance zero-copy cuda high-performance-computing compiler-optimization interconnect silicon-photonics jax pytorch-extension xla custom-kernels hardware-software-co-design ahead-of-time-compilation ai-infrastructure llm-infrastructure deepseek-v4 ptx-assembly hlo-compiler
-
Updated
Aug 9, 2026 - Python
Pre-compiled custom CUDA extension for Block Sparse Attention (Python 3.11 / PyTorch 2.6.0+cu124).
python machine-learning cuda pytorch pytorch-extension llm-optimization cuda-12 block-sparse-attention precompiled-wheel
-
Updated
May 4, 2026
Binding C++ to PyTorch and extending PyTorch
-
Updated
Nov 2, 2022 - Python
PyTorch extension for alternative backward rules and gradient transforms (STE, gradient jamming, non-standard activations).
training research deep-learning python3 pytorch autograd neural-networks gradient backpropagation binary-neural-networks activation-functions gradient-clipping pytorch-extension gradient-modification
-
Updated
Nov 30, 2025 - Python
Input-aware CUDA auto-scheduler for CSR SpMM, SDDMM, and sparse attention in graph neural networks.
cuda pytorch high-performance-computing graph-processing sparse-matrix auto-tuning graph-neural-networks pytorch-extension spmm sddmm
-
Updated
Jul 22, 2026 - Python
Inference stack that keeps LLM weights packed in NF4 for the whole run. Not a new codebook: QLoRA-family NF4, packed once into CHR0. On the GPU each GEMM reconstructs a tile in registers and discards it, a dense layer is never resident. Overflow: two copy slots plus a pinned host tail. Measured on RTX 3080 12 GB.
go deep-learning gpu cuda transformer quantization ampere inference-engine model-compression 4-bit pytorch-extension huggingface cuda-kernel llm internlm qwen nf4
-
Updated
Sep 18, 2026 - Python
performance-engineering cuda cuda-kernels gpu-programming pytorch-extension parellel-programming flashattention kernel-optimization
-
Updated
May 13, 2026 - Cuda
CUDA/PyTorch operator for fused neighborhood sampling and mean aggregation, with reproducible KSEM 2026 experiments.
reproducible-research cuda pytorch high-performance-computing graph-processing gpu-computing graph-neural-networks pytorch-extension knowledge-graphs neighbor-sampling
-
Updated
Jul 22, 2026 - Python
Add this topic to your repo
To associate your repository with the pytorch-extension topic, visit your repo's landing page and select "manage topics."