LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalability, and high-speed performance.
-
Updated
Sep 6, 2026 - Python
#
openai-triton
Here are 7 public repositories matching this topic...
https://wavespeed.ai/ Best inference performance optimization framework for HuggingFace Diffusers on NVIDIA GPUs.
cuda torch pytorch inference-engines performance-optimizations stable-diffusion diffusers deeplearnng openai-triton stable-video-diffusion
-
Updated
Mar 27, 2025 - Python
A subset of PyTorch's neural network modules, written in Python using OpenAI's Triton.
-
Updated
Aug 14, 2026 - Python
Training-free Post-training Efficient Sub-quadratic Complexity Attention. Implemented with OpenAI Triton.
-
Updated
Mar 31, 2026 - Python
RootMeanSquareNorm + Rotary Position Embedding - Triton Kernel Optimization
pytorch rope rotary-position-embedding rmsnorm openai-triton triton-language triton-kernels throughput-optimization
-
Updated
Aug 3, 2026 - Python
High-performance Fused RMSNorm kernel powered by OpenAI Triton, achieving memory-bandwidth saturation on consumer GPUs (RTX 3060/4060) for LLM Inference.
-
Updated
Jul 29, 2026
Add this topic to your repo
To associate your repository with the openai-triton topic, visit your repo's landing page and select "manage topics."