Tag

#gpu

Guides, tutorials and insights about gpu — written from hands-on experience.

📚 7 articles
Deploying Local DeepSeek-R1 Reasoning Models with vLLM and TensorRT-LLM on Linux
Technology · 29 Oct 2026

Deploying Local DeepSeek-R1 Reasoning Models with vLLM and TensorRT-LLM on Linux

In 2026, artificial intelligence and enterprise workflow automation have evolved into essential drivers of business resilience and computational efficiency. Designing scalable agentic systems and high-throughput pipelines requires deterministic orchestration, intelligent caching, and multi-layered fault…

Read article
Fine-Tuning Llama 3.3 70B with LoRA and Unsloth for Domain-Specific Technical Support
AI · 27 Oct 2026

Fine-Tuning Llama 3.3 70B with LoRA and Unsloth for Domain-Specific Technical Support

In 2026, artificial intelligence and enterprise workflow automation have evolved into essential drivers of business resilience and computational efficiency. Designing scalable agentic…

Read article
Deploying Open-Source DeepSeek-Coder Models on Bare-Metal GPUs with vLLM and Docker
Technology · 22 Apr 2026

Deploying Open-Source DeepSeek-Coder Models on Bare-Metal GPUs with vLLM and Docker

In the evolving landscape of enterprise technology, automation and artificial intelligence have transitioned from experimental tools into critical infrastructure. Scaling high-throughput data…

Read article
Fine-Tuning Llama 3 8B with Unsloth on Consumer GPUs in Under 30 Minutes
AI · 23 Mar 2026

Fine-Tuning Llama 3 8B with Unsloth on Consumer GPUs in Under 30 Minutes

In the evolving landscape of enterprise technology, automation and artificial intelligence have transitioned from experimental tools into critical infrastructure. Scaling high-throughput data…

Read article
Deploying Highly Available Mistral NeMo Models with TensorRT-LLM and Triton
AI · 15 Mar 2026

Deploying Highly Available Mistral NeMo Models with TensorRT-LLM and Triton

In the evolving landscape of enterprise technology, automation and artificial intelligence have transitioned from experimental tools into critical infrastructure. Scaling high-throughput data…

Read article
Deploying Local Embedding Models with Infinity and ONNX Runtime for 10x Lower Latency
AI · 2 Jan 2026

Deploying Local Embedding Models with Infinity and ONNX Runtime for 10x Lower Latency

In the evolving landscape of enterprise technology, automation and artificial intelligence have transitioned from experimental tools into critical infrastructure. Scaling high-throughput data…

Read article
Deploying Quantized DeepSeek-R1 Models on Local Hardware with ExLlamaV2 and vLLM
AI · 3 Nov 2025

Deploying Quantized DeepSeek-R1 Models on Local Hardware with ExLlamaV2 and vLLM

In the evolving landscape of enterprise technology, automation and artificial intelligence have transitioned from experimental tools into critical infrastructure. Scaling high-throughput data…

Read article
Work with me

Want results like this for your business?

AI agents, custom software, websites and growth systems — let’s talk about yours.