--- title: "#triton articles | Hashnode" description: "Explore 9 articles tagged #triton on Hashnode. Tutorials, guides, and how-tos from the community." url: "https://hashnode.com/tag/triton" --- Tag # #triton 9 posts · 0 followers [Aleksei Romanov](https://hashnode.com/@gfactor) · [Nov 3](https://hashnode.com/posts/teaching-a-27b-model-to-write-triton-kernels-sft-rl-gym/6aea252b0aa43068615c154e) ### [Teaching a 27B Model to Write Triton Kernels: SFT + RL Gym](https://gfactor.hashnode.dev/teaching-a-27b-model-to-write-triton-kernels-sft-rl-gym?utm_source=hashnode&utm_medium=feed) In Part 1, we explored how GPU kernels work under the hood — why operator fusion and memory tiling matter, and how benchmarks like KernelBench evaluate whether an LLM can write kernels that actually b 27 min read · [gfactor.hashnode.dev](https://gfactor.hashnode.dev/teaching-a-27b-model-to-write-triton-kernels-sft-rl-gym?utm_source=hashnode&utm_medium=feed) [Aleksei Romanov](https://hashnode.com/@gfactor) · [Nov 3](https://hashnode.com/posts/gpu-kernels-explained-cuda-triton-cublas-torch-compile-and-kernelbench/6ae986128db764f898d76a12) ### [GPU Kernels, Explained: CUDA, Triton, cuBLAS, torch.compile and KernelBench](https://gfactor.hashnode.dev/gpu-kernels-explained-cuda-triton-cublas-torch-compile-and-kernelbench?utm_source=hashnode&utm_medium=feed) When you run a neural network in PyTorch, Python is only the coordinator. Behind every tensor operation — from a simple activation to a multi-head attention block — sits one or more GPU kernels: speci 28 min read · [gfactor.hashnode.dev](https://gfactor.hashnode.dev/gpu-kernels-explained-cuda-triton-cublas-torch-compile-and-kernelbench?utm_source=hashnode&utm_medium=feed) [Arpit Singh Gautam](https://hashnode.com/@arpitsinghgautam) · [Jul 25](https://hashnode.com/posts/rebuilding-triton-and-helion-from-scratch-in-4-000-lines-of-python/6a64c750477895606cb241a9) ### [Rebuilding Triton and Helion from Scratch in 4,000 Lines of Python](https://arpitsinghgautam.hashnode.dev/rebuilding-triton-and-helion-from-scratch-in-4-000-lines-of-python?utm_source=hashnode&utm_medium=feed) A from-scratch nano-Triton and nano-Helion, at memory-bandwidth parity with Triton and ~92% of its cold matmul 11 min read · [arpitsinghgautam.hashnode.dev](https://arpitsinghgautam.hashnode.dev/rebuilding-triton-and-helion-from-scratch-in-4-000-lines-of-python?utm_source=hashnode&utm_medium=feed) [5](https://hashnode.com/posts/rebuilding-triton-and-helion-from-scratch-in-4-000-lines-of-python/6a64c750477895606cb241a9) [Nguyễn Hữu Đức](https://hashnode.com/@ducnguyen-creator) · [Jul 11](https://hashnode.com/posts/draco-ai/6a51b42422570cdfac8f9efd) ### [Building an LLM System from Scratch in Pure Python & NumPy: Architecture, Invariants, and Clean Code, Open-Source 100% Inference Engine and Thinking engine!](https://draco-ai.hashnode.dev/draco-ai?utm_source=hashnode&utm_medium=feed) Exploring the design invariants, ternary quantization, and self-healing cognitive pipeline of Draco AI, a hardware-agnostic LLM built from scratch. 3 min read · [draco-ai.hashnode.dev](https://draco-ai.hashnode.dev/draco-ai?utm_source=hashnode&utm_medium=feed) [Nir Adler](https://hashnode.com/@niradler) · [May 29, 2025](https://hashnode.com/posts/gpu-inference-servers-comparison-triton-vs-tgi-vs-vllm-vs-ollama/68383125421e876463bb185e) ### [GPU Inference Servers Comparison: Triton vs TGI vs vLLM vs Ollama](https://blog.niradler.com/gpu-inference-servers-comparison-triton-vs-tgi-vs-vllm-vs-ollama?utm_source=hashnode&utm_medium=feed) The landscape of GPU inference servers has evolved dramatically, with several powerful solutions competing for dominance in serving large language models (LLMs) and other AI workloads. As organizations scale their AI deployments, choosing the right i... 8 min read · [blog.niradler.com](https://blog.niradler.com/gpu-inference-servers-comparison-triton-vs-tgi-vs-vllm-vs-ollama?utm_source=hashnode&utm_medium=feed) [shes](https://hashnode.com/@shes) · [Oct 12, 2022](https://hashnode.com/posts/why-i-decided-to-use-nvidia-triton-for-inference/6346564024ef8cc3fa917fa1) ### [Why I decided to use NVIDIA Triton for inference](https://shes.hashnode.dev/why-i-decided-to-use-nvidia-triton-for-inference?utm_source=hashnode&utm_medium=feed) Why I decided to use NVIDIA Triton for inference of neural networks 4 min read · [shes.hashnode.dev](https://shes.hashnode.dev/why-i-decided-to-use-nvidia-triton-for-inference?utm_source=hashnode&utm_medium=feed)