56,966 blogs · [ { "id": "01a0875d-93f4-7051-86de-2f67d74845e0", "title": "How Profitable is LLM Inference? Doing the Math on Kimi K3", "url": "https://cefboud.com/posts/ai-inference-costs-profit/", "published_at": "2026-07-29T00:00:00+00:00" }, { "id": "01a0875d-93f4-7051-86de-2f67d7747a70", "title": "Distributed LLM Inference with llm-d", "url": "https://cefboud.com/posts/llm-d/", "published_at": "2026-06-21T00:00:00+00:00" }, { "id": "01a0875d-93f4-7051-86de-2f67d79e6bfe", "title": "Exploring Speculative Decoding: From Concept to Implementation", "url": "https://cefboud.com/posts/speculative-decoding/", "published_at": "2026-05-31T00:00:00+00:00" }, { "id": "01a0875d-93f4-7051-86de-2f67d8826912", "title": "Exploring Mixture of Experts: From Concept to Inference Engine", "url": "https://cefboud.com/posts/mixture-of-experts-MoE-nano-vllm-deep-dive/", "published_at": "2026-04-26T00:00:00+00:00" }, { "id": "01a0875d-93f4-7051-86de-2f67d96187ee", "title": "Deep Dive into Efficient LLM Inference with nano-vLLM", "url": "https://cefboud.com/posts/inside-llm-inference-engine-nano-vllm-explanation/", "published_at": "2026-04-05T00:00:00+00:00" }, { "id": "01a087ac-dccd-7076-9336-9f1c69fe7f33", "title": "Linklog | Taking a Look at Compression Algorithms", "url": "https://cefboud.com/posts/compression/", "published_at": "2025-02-09T12:00:00+00:00" } ] posts Claim your blog

Blog · corpus.blog/blogs/cefboud.com/posts