Accelerate your models with 🤗 Optimum Intel and OpenVINO

Optimize and deploy with Optimum-Intel and OpenVINO GenAI

Accelerating Qwen3-8B Agent on Intel® Core™ Ultra with Depth-Pruned Draft Models

How 🤗 Accelerate runs very large models thanks to PyTorch

Accelerating PyTorch distributed fine-tuning with Intel technologies

Accelerate Large Model Training using DeepSpeed

Accelerating engineering cycles 20% with OpenAI

Accelerating engineering cycles 20% with OpenAI.

Accelerate Large Model Training using PyTorch Fully Sharded Data Parallel

Performance Optimization and Comparative Analysis of Generative AI Models on Advanced Accelerators

arXiv:2607. 05400v1 Announce Type: cross Abstract: Generative AI models, such as Large Language Models (LLMs) and diffusion models, have demonstrated impressive performance across a wide range of tasks.

OlmoEarth v1.2: A more efficient family of OlmoEarth models

arXiv:2605. 20804v2 Announce Type: replace-cross Abstract: We present a set of improvements to the OlmoEarth family.

Tile-Level Activation Overlap for Efficient LLM Inference

arXiv:2607. 02521v1 Announce Type: cross Abstract: SwiGLU is the dominant MLP activation in modern large language models, yet its intermediate tensor materialization costs 9-37% of MLP execution time.

Qwen 3.8 27B is excellent, but it defaults to wildly overthinking things

Friday's big release was Qwen 3. 8 27B , an Apache 2 licensed 27B parameter vision-capable LLM from Alibaba's Qwen research lab.

Pre-Compiled Pipeline Shards for Distributed LLM Inference on Intel AI PC Fleets

The paper presents a method for distributing large language model inference across multiple Intel AI PCs by splitting the model into pipeline shards, each pre‑compiled into an OpenVINO graph. Three key techniques—beam_idx Gather to enable GPU optimizations, speculative decoding on stateful models, and interleaved micro‑batching—allow a two‑node Llama 3.1 8B INT4 pipeline to serve two users at 1.79× the throughput of a single‑node model, while a four‑node deployment can run a 70B model that no single PC can hold. The authors provide code, benchmark logs, and reproduction scripts on GitHub.