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
DeepSeek-V4 Flash RL on AMD Instinct MI308X GPUs with an AITER-Backed RL Stack
Run end-to-end DeepSeek-V4 Flash reinforcement learning with an AITER-backed AMD RL stack on AMD Instinct MI308X GPUs.
Efficient MiniMax-M3 Inference on AMD Instinct GPUs with ATOM and ATOMesh
Serve and benchmark MiniMax-M3 on AMD Instinct MI355X GPUs using ATOM and ATOMesh with EAGLE3 speculative decoding.
SPIR-V on ROCm: A Portable IR for AMD GPUs
Learn how SPIR-V brings compile-once, specialize-on-device portability to AMD GPUs — with a reproducible HIP benchmark, trade-off analysis, and quick-start guide.
OpenXLA and JAX - ROCm Support and the State of CI
Learn how OpenXLA and JAX run on AMD ROCm: what landed this year, how every PR is gated on real Instinct hardware, and how to get started.
Getting Started with FlyDSL Nightly Wheels on ROCm
A practical guide to installing and using FlyDSL nightly wheels on ROCm for fast, Python-native GPU kernel development
PyTorch Offline Tuning with TunableOp
Learn how to accelerate PyTorch workloads with TunableOp offline tuning—record, tune separately, and deploy faster inference.
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.
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.
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.
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.
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.
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
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.