Hongxia Yang

Hongxia Yang is hands-on Software Engineer tech leader. Her work in AMD is devoted to advancing and accelerating AI/ML (Gen AI, etc) with PyTorch, vLLM, and GPU Computing. Throughout her career, she has had an extensive track record of industrial success in C/C++, JAVA and Python programming and project leadership in Distributed Systems focusing on AI/ML Infrastructure and Trading systems. She received her MS in Computer Science from Tsinghua University.

Posts by Hongxia Yang

February 24, 2026

PyTorch Offline Tuning with TunableOp

Learn how to accelerate PyTorch workloads with TunableOp offline tuning—record, tune separately, and deploy faster inference.

https://rocm.blogs.amd.com/artificial-intelligence/pytorch-tunableop-offline/README.html

February 20, 2026

FlyDSL: Expert GPU Kernel Development with the Ease of MLIR Python Native DSL on AMD GPUs

FlyDSL is a Python-first, MLIR-native DSL for expert GPU kernel development and tuning on AMD GPUs.

https://rocm.blogs.amd.com/software-tools-optimization/flydsl-python-native/README.html

January 21, 2026

ROCm Becomes a First-Class Platform in the vLLM Ecosystem

ROCm is now a first-class vLLM platform: official wheels + Docker, stronger CI, and faster LLM & multimodal inference on AMD Instinct GPUs.

https://rocm.blogs.amd.com/software-tools-optimization/vllm-omni/README.html

January 02, 2026

Accelerating Multimodal Inference in vLLM: The One-Line Optimization for Large Multimodal Models

Learn how to optimize multimodal model inference with batch-level data parallelism for vision encoders in vLLM, achieving up to 45% throughput gains on AMD MI300X.

https://rocm.blogs.amd.com/software-tools-optimization/vllm-dp-vision/README.html

November 24, 2025

The vLLM MoE Playbook: A Practical Guide to TP, DP, PP and Expert Parallelism

Learn how to combine TP, DP, PP, and EP for MoE models. Discover proven strategies to maximize performance on your vLLM deployments.

https://rocm.blogs.amd.com/software-tools-optimization/vllm-moe-guide/README.html

October 21, 2025

Empowering Developers to Build a Robust PyTorch Ecosystem on AMD ROCm™ with Better Insights and Monitoring

Production ROCm support for N-1 to N+1 PyTorch releases is in progress. The AI Software Head-Up Dashboard shows status of PyTorch on ROCm.

https://rocm.blogs.amd.com/artificial-intelligence/pytorch-amd-gpus/README.html

August 05, 2025

Day 0 Developer Guide: Running the Latest Open Models from OpenAI on AMD AI Hardware

Day 0 support across our AI hardware ecosystem from our flagship AMD InstinctTM MI355X and MI300X GPUs, AMD Radeon™ AI PRO R700 GPUs and AMD Ryzen™ AI Processors

https://rocm.blogs.amd.com/ecosystems-and-partners/openai-day-0/README.html

June 28, 2025

Accelerated LLM Inference on AMD Instinct™ GPUs with vLLM 0.9.x and ROCm

vLLM v0.9.x is here with major ROCm™ optimizations—boosting LLM performance, reducing latency, and expanding model support on AMD Instinct™ GPUs.

https://rocm.blogs.amd.com/software-tools-optimization/vllm-0.9.x-rocm/README.html