https://cefboud.com/Moncef AbboudMoncef Abboud blog and posts. 2026-09-22T22:48:08+00:00 Moncef Abboud https://cefboud.com/ Jekyll © 2026 Moncef Abboud /assets/img/favicons/favicon.ico /assets/img/favicons/favicon-96x96.png How Profitable is LLM Inference? Doing the Math on Kimi K32026-07-29T00:00:00+00:00 2026-07-29T00:00:00+00:00 https://cefboud.com/posts/ai-inference-costs-profit/ cef A look at LLM inference economics (batch size, GPU count, and the Pareto frontier that sets token prices) applied to Kimi K3 with back-of-the-envelope math. Distributed LLM Inference with llm-d2026-06-21T00:00:00+00:00 2026-06-21T00:00:00+00:00 https://cefboud.com/posts/llm-d/ cef An introduction to llm-d, an open-source LLM-aware router that intelligently schedules requests across inference engines like vLLM using KV cache locality and GPU utilization. Exploring Speculative Decoding: From Concept to Implementation2026-05-31T00:00:00+00:00 2026-05-31T00:00:00+00:00 https://cefboud.com/posts/speculative-decoding/ cef In this post, we explore speculative decoding through a concrete vLLM-focused implementation, covering draft models, EAGLE, MTP, and the tradeoffs involved. Exploring Mixture of Experts: From Concept to Inference Engine2026-04-26T00:00:00+00:00 2026-04-26T00:00:00+00:00 https://cefboud.com/posts/mixture-of-experts-MoE-nano-vllm-deep-dive/ cef In this post, we dabble in Mixture of Experts (MoE) models through a concrete nano-vLLM implementation, exploring Triton kernels, expert parallelism, and other fun things. Deep Dive into Efficient LLM Inference with nano-vLLM2026-04-05T00:00:00+00:00 2026-04-05T00:00:00+00:00 https://cefboud.com/posts/inside-llm-inference-engine-nano-vllm-explanation/ cef A look inside a lightweight implementation of vLLM. KV cache, paged attention, tensor parallelism &multi-GPU support, etc.