AI Developer Hub tutorial selector

Use the following matrix to determine which tutorials might be suitable for you. Select a knowledge level and a tutorial type, and the matching tutorials will be displayed below.

Knowledge level

All

Beginner

Intermediate

Advanced

Tutorial type

All

Inference

Fine-tuning

Pretraining

GPU Dev & Optimization

---

Here are the selected tutorials.

Inference tutorials

• ChatQnA vLLM deployment and performance evaluation

• Text-to-video generation with ComfyUI

• Running ComfyUI generative workflows from Python on AMD Instinct GPUs

• DeepSeek Janus Pro on CPU or GPU

• DeepSeek-R1 with vLLM V1

• AI agent with MCPs using vLLM and PydanticAI

• Hugging Face Transformers

• Deploying with vLLM

• From chatbot to rap bot with vLLM

• RAG with LlamaIndex and Ollama

• OCR with vision-language models with vLLM

• Building AI pipelines for voice assistants

• Speculative decoding with vLLM

• DeepSeek-R1 with SGLang

• PD disaggregation with SGLang

• Accelerating DeepSeek-V3 inference using multi-token prediction in SGLang

• Multi-agents with Google ADK and A2A protocol

• Deploy OpenClaw with Qwen3.5 and vLLM

• Multi-agent incident triage with OpenClaw on AMD Instinct

Fine-tuning tutorials

• Customize Qwen-Image with DiffSynth-Studio

• VLM with PEFT

• Llama-3.1 8B with torchtune

• Llama-3.1 8B with Llama-Factory

• GRPO with Unsloth

• GRPO with slime

Pretraining tutorials

• Training configuration with Megatron-LM

• LLM with Megatron-LM

• Llama-3.1 8B with torchtitan

• Custom diffusion model with PyTorch

• Speculative decoding draft model with SpecForge

• Pretraining with TorchTitan

• Training a model with Primus

• SE(3)-Transformer overview

• Training and serving a FinalNet CTR model with Triton Inference Server

GPU development and optimization tutorials

• Quark MXFP4 quantization for vLLM

• GPU kernel development and assessment with Helion

• MLA decoding kernel of AITER library

• Kernel development and optimization with Triton

• Profiling Llama-4 inference with vLLM

• FP8 quantization with AMD Quark for vLLM

• FP8 GEMM optimization on AMD CDNA4-based GPUs

• ChatQnA vLLM deployment and performance evaluation

• Text-to-video generation with ComfyUI

• Running ComfyUI generative workflows from Python on AMD Instinct GPUs

• DeepSeek Janus Pro on CPU or GPU

• DeepSeek-R1 with vLLM V1

• AI agent with MCPs using vLLM and PydanticAI

• Hugging Face Transformers

• Deploying with vLLM

• From chatbot to rap bot with vLLM

• RAG with LlamaIndex and Ollama

• OCR with vision-language models with vLLM

• Building AI pipelines for voice assistants

• Speculative decoding with vLLM

• DeepSeek-R1 with SGLang

• PD disaggregation with SGLang

• Accelerating DeepSeek-V3 inference using multi-token prediction in SGLang

• Multi-agents with Google ADK and A2A protocol

• Deploy OpenClaw with Qwen3.5 and vLLM

• Multi-agent incident triage with OpenClaw on AMD Instinct

• Customize Qwen-Image with DiffSynth-Studio

• VLM with PEFT

• Llama-3.1 8B with torchtune

• Llama-3.1 8B with Llama-Factory

• GRPO with Unsloth

• GRPO with slime

• Training configuration with Megatron-LM

• LLM with Megatron-LM

• Llama-3.1 8B with torchtitan

• Custom diffusion model with PyTorch

• Speculative decoding draft model with SpecForge

• Pretraining with TorchTitan

• Training a model with Primus

• SE(3)-Transformer overview

• Training and serving a FinalNet CTR model with Triton Inference Server

• Quark MXFP4 quantization for vLLM

• GPU kernel development and assessment with Helion

• MLA decoding kernel of AITER library

• Kernel development and optimization with Triton

• Profiling Llama-4 inference with vLLM

• FP8 quantization with AMD Quark for vLLM

• FP8 GEMM optimization on AMD CDNA4-based GPUs

• ChatQnA vLLM deployment and performance evaluation

• Text-to-video generation with ComfyUI

• DeepSeek Janus Pro on CPU or GPU

• DeepSeek-R1 with vLLM V1

• AI agent with MCPs using vLLM and PydanticAI

• Hugging Face Transformers

• Deploying with vLLM

• From chatbot to rap bot with vLLM

• RAG with LlamaIndex and Ollama

• OCR with vision-language models with vLLM

• Building AI pipelines for voice assistants

• DeepSeek-R1 with SGLang

• Deploy OpenClaw with Qwen3.5 and vLLM

• Custom diffusion model with PyTorch

• Training and serving a FinalNet CTR model with Triton Inference Server

• Quark MXFP4 quantization for vLLM

• Speculative decoding with vLLM

• PD disaggregation with SGLang

• Accelerating DeepSeek-V3 inference using multi-token prediction in SGLang

• Multi-agents with Google ADK and A2A protocol

• Running ComfyUI generative workflows from Python on AMD Instinct GPUs

• Multi-agent incident triage with OpenClaw on AMD Instinct

• Customize Qwen-Image with DiffSynth-Studio

• VLM with PEFT

• Llama-3.1 8B with torchtune

• Llama-3.1 8B with Llama-Factory

• GRPO with Unsloth

• GRPO with slime

• Training configuration with Megatron-LM

• LLM with Megatron-LM

• Llama-3.1 8B with torchtitan

• Speculative decoding draft model with SpecForge

• Pretraining with TorchTitan

• Training a model with Primus

• SE(3)-Transformer overview

• GPU kernel development and assessment with Helion

• MLA decoding kernel of AITER library

• Kernel development and optimization with Triton

• Profiling Llama-4 inference with vLLM

• FP8 quantization with AMD Quark for vLLM

• FP8 GEMM optimization on AMD CDNA4-based GPUs