November 18, 2024
Distilling Llama3.1 8B into 1B in torchtune
In this blog, we present a case study on distilling a Llama 3.1 8B model into Llama 3.2 1B using torchtune’s knowledge distillation recipe. We demonstrate how knowledge distillation (KD) can be used in post-training to improve instruction-following task performance and showcase how users can leverage the recipe.
November 01, 2024
Deep Dive on CUTLASS Ping-Pong GEMM Kernel
In this post, we provide an overview, with relevant FP8 inference kernel benchmarking, of the CUTLASS Ping-Pong GEMM kernel.
October 31, 2024
Deploying LLMs with TorchServe + vLLM
The vLLM engine is currently one of the top-performing ways to execute large language models (LLM). It provides the vllm serve command as an easy option to deploy a model on a single machine. While this is convenient, to serve these LLMs in production and at scale some advanced features are necessary.
October 30, 2024
Triton Kernel Compilation Stages
The Triton open-source programming language and compiler offers a high-level, python-based approach to create efficient GPU code. In this blog, we highlight the underlying details of how a triton program is compiled and the intermediate representations. For an introduction to Triton, we refer readers to this blog.
October 28, 2024
Unleashing the Power of AI on Mobile: LLM Inference for Llama 3.2 Quantized Models with ExecuTorch and KleidiAI
At the recent PyTorch Conference, Arm highlighted the widespread impact of its technology, spanning from cloud to edge, emphasizing its commitment to delivering its advanced AI computing capabilities seamlessly to millions of developers worldwide.
October 28, 2024
Getting started with PyTorch, ExecuTorch, and Ethos-U85 in three easy steps
ExecuTorch support for Ethos-U85
October 25, 2024
Intel GPU Support Now Available in PyTorch 2.5
Support for Intel GPUs is now available in PyTorch® 2.5, providing improved functionality and performance for Intel GPUs which including Intel® Arc™ discrete graphics, Intel® Core™ Ultra processors with built-in Intel® Arc™ graphics and Intel® Data Center GPU Max Series. This integration brings Intel GPUs and the SYCL* software stack into the official PyTorch stack, ensuring a consistent user experience and enabling more extensive AI application scenarios, particularly in the AI PC domain.
