Corporate AI & Technology Training Catalog

Local & On-Premise LLM Platforms LLM Model Serving and Deployment Fundamentals RuneLab Academy · 12 hours

Shows how an open-weight LLM is served as an OpenAI-compatible API on a GPU server: inference engines, VRAM math, core serving settings and a first benchmark. An entry-level programme for developer and platform teams.

12 hours

Live Course

5 modules

Local & On-Premise LLM Platforms LLM Serving with vLLM: Production Inference Deployment RuneLab Academy · 12 hours

High-throughput LLM serving with vLLM: PagedAttention, continuous batching, tensor parallelism, prefix caching, multi-LoRA serving and Prometheus metrics. Teams leave with a production-ready vLLM deployment and benchmark report.

12 hours

Live Course

5 modules

Local & On-Premise LLM Platforms Hugging Face Text Generation Inference (TGI) for LLM Serving RuneLab Academy · 12 hours

Serving LLMs with Hugging Face Text Generation Inference (TGI): Docker setup, sharding, quantization, Messages API, structured output with guidance and Inference Endpoints. A hands-on programme for teams in the Hugging Face ecosystem.

12 hours

Live Course

5 modules

Local & On-Premise LLM Platforms Running Local LLMs with Ollama RuneLab Academy · 12 hours

Running open-weight models on laptops, workstations or servers with Ollama: model library, Modelfile, REST/OpenAI-compatible API, Open WebUI, embeddings and a shared team setup. For fast prototyping and confidential-data scenarios.

12 hours

Live Course

5 modules

Local & On-Premise LLM Platforms LLM Serving Stack Mastery: FastAPI, vLLM, KServe and Triton RuneLab Academy · 18 hours

Combines a FastAPI model API layer, vLLM for LLM inference, KServe for model management on Kubernetes and Triton for multi-framework serving in one architecture. Participants build an end-to-end, scalable model serving stack.

18 hours

Live Course

6 modules

Local & On-Premise LLM Platforms LLM Quantization: INT8, INT4, FP8, FP16 and BF16 in Practice RuneLab Academy · 12 hours

FP16/BF16, FP8, INT8 and INT4 precision options for LLMs; post-training quantization with GPTQ, AWQ, GGUF and bitsandbytes, measuring quality loss with evals and verifying VRAM and throughput gains through benchmarks.

12 hours

Live Course

5 modules

Local & On-Premise LLM Platforms Dynamic Quantization for Neural Networks and LLMs RuneLab Academy · 12 hours

Accelerating models with dynamic quantization without calibration data: PyTorch and ONNX Runtime dynamic quantization, FP8 dynamic activation scaling, comparison with static methods and measurement on CPU and GPU.

12 hours

Live Course

5 modules

Local & On-Premise LLM Platforms Quantization-Aware Training, QLoRA Fine-Tuning and Quantized Serving RuneLab Academy · 12 hours

Covers quantization end to end from training to serving: 4-bit fine-tuning with QLoRA, quantization-aware training (QAT), merging adapters, re-quantizing and serving in vLLM. For teams adapting models to company data on a single GPU.

12 hours

Live Course

5 modules

Local & On-Premise LLM Platforms GPU Capacity Planning and Hardware Sizing for LLM Inference RuneLab Academy · 12 hours

GPU capacity planning for LLM workloads: deriving VRAM, GPU count and server needs from model size, context length, concurrent users and SLO targets, plus a cost comparison of H100/H200/B200, L40S and cloud options.

12 hours

Live Course

5 modules

Local & On-Premise LLM Platforms In-House LLM Platform Architecture: From Hardware Sizing to Air-Gapped Production RuneLab Academy · 12 hours

End-to-end in-house LLM platform design for data residency and regulated environments: GPU sizing, Kubernetes cluster, vLLM/Triton serving, model gateway, security and air-gapped production architecture. Built for platform and infrastructure teams.

12 hours

Live Course

5 modules

Local & On-Premise LLM Platforms Air-Gapped LLM Deployment, Offline Registry Mirroring and Update Operations RuneLab Academy · 12 hours

Deploying and updating LLM services in air-gapped networks: offline container, PyPI and Hugging Face mirroring, safetensors and SBOM verification, GPU driver bundling and zero-downtime patching. Built for security-focused platform teams.

12 hours

Live Course

5 modules

Local & On-Premise LLM Platforms Running Local LLMs on Desktop and Workstations: llama.cpp, GGUF and LM Studio RuneLab Academy · 12 hours

Running local LLMs on desktops and workstations with llama.cpp, GGUF and LM Studio: k-quant selection, CPU+GPU layer offloading, Metal/CUDA/Vulkan acceleration and local OpenAI-compatible APIs. For developers and analysts.

12 hours

Live Course

5 modules

Local & On-Premise LLM Platforms Self-Hosted AI Coding Assistants with Local LLMs RuneLab Academy · 12 hours

Building self-hosted AI coding assistants without sending source code outside the company: Qwen2.5-Coder and DeepSeek-Coder models, FIM autocomplete, Continue.dev/Tabby IDE plugins, vLLM serving and codebase RAG integration.

12 hours

Live Course

5 modules

Local & On-Premise LLM Platforms Open-Weight LLM Selection, Licensing and Benchmarking for Enterprise Use RuneLab Academy · 12 hours

Selecting open-weight LLMs for enterprise use: Llama, Qwen, Mistral, Gemma and DeepSeek families; commercial licence analysis, dense vs MoE trade-offs, Turkish and tool-calling capability, and building a benchmark matrix on company data.

12 hours

Live Course

5 modules

Local & On-Premise LLM Platforms Enterprise Model Serving with NVIDIA Triton Inference Server and KServe RuneLab Academy · 12 hours

Multi-model GPU serving with NVIDIA Triton Inference Server and KServe: TensorRT-LLM, ONNX and Python backends, dynamic batching, model ensembles, KServe InferenceService, Knative autoscaling and tuning with Model Analyzer.

12 hours

Live Course

5 modules

Local & On-Premise LLM Platforms KV Cache Management and Continuous Batching Optimization for LLM Inference RuneLab Academy · 12 hours

Solving memory and concurrency bottlenecks in LLM serving: KV cache memory math, PagedAttention, SGLang RadixAttention, prefix caching, FP8 KV cache quantization, continuous batching and chunked prefill tuning.

12 hours

Live Course

5 modules

Local & On-Premise LLM Platforms LLM Inference Throughput and Latency Optimization RuneLab Academy · 12 hours

Optimising TTFT, ITL and total throughput in LLM services: compute-bound vs memory-bandwidth-bound bottleneck analysis, FlashAttention/FlashInfer, CUDA Graphs, speculative decoding, parallelism tuning and SLO-driven load testing.

12 hours

Live Course

5 modules

Local & On-Premise LLM Platforms Running AI and LLM Workloads on Kubernetes RuneLab Academy · 18 hours

Operating GPU and LLM workloads on Kubernetes: NVIDIA GPU Operator, GPU sharing with MIG and time-slicing, queue management with Kueue/Volcano, fast model weight caching, GPU autoscaling and DCGM observability.

18 hours

Live Course

5 modules