tr7200 / Adam_to_SGD Star 5 Code Issues Pull requests Tensorflow-Keras callback implementing arXiv 1712.07628 keras-callback sgd-optimizer custom-callback early-stopping tensorflow-keras swats deep-learning-optimization swats-algorithm optimizer-switching generalization-performance Updated Mar 24, 2023 Python
pauliano22 / triton-gpu-kernels Star 2 Code Issues Pull requests High-performance Triton kernels for NVIDIA H100. Implements fused FP8 LayerNorm, tiled FlashAttention, and SRAM-optimized memory primitives for Hopper architecture. parallel-computing cuda triton gpu-kernels fp8 h100 deep-learning-optimization llm-infrastructure Updated Oct 13, 2026 Python
mslawsky / learning-rate-optimization Star 0 Code Issues Pull requests This repository documents the process of finding the optimal learning rate for deep neural networks time-series-forecasting ml-engineering training-dynamics neural-network-training tensorflow-optimization learning-rate-optimization deep-learning-optimization Updated Jun 3, 2025
anmolsharma152 / cuda-tensorrt-vllm-lab Star 0 Code Issues Pull requests Production-grade engineering testbed and conceptual knowledge base for CUDA, TensorRT, vLLM, SGLang, Megatron-LM, and Agentic AI. cuda pytorch gpu-computing tensorrt distributed-training megatron-lm vllm llm-inference paged-attention sglang agentic-ai deep-learning-optimization Updated Oct 15, 2026 Python