Wei LuLlama3–70B inference on Intel Core Ultra 5 125HAs mentioned in the prior blog, i’ve got a mini-pc with an Intel Core Ultra 5 125H and 96GB DDR5 5600 DRAM. Today i tried llama-3 70b in…·1 min read·May 27, 2024----
Wei LuIntel Core Ultra 5 vs. Apple M1 on LLM inferenceI bought an Intel “AI PC” equipped with a Core Ultra 5 125H and 96GB of memory, which means a graphics card with 48GB of VRAM. This mini PC…·3 min read·May 24, 2024----
Wei LuNext generation of UIThe release of AI PCs by Intel and AMD didn’t cause much of a stir, but Microsoft’s release of the AI PC concept, “Copliot+PC”, has brought…·2 min read·May 21, 2024----
Wei LuLLM for Coding, the State and Initiatives, Part 2Continuing from where we left off.·8 min read·May 20, 2024----
Wei LuLLM for Coding, the State and InitiativesAt the AI & Agents Forum of GOSIM Europe 2024 conference on May 6th at Delft, The Netherlands, I, as a guest speaker, delivered a speech…·5 min read·May 17, 2024----
Wei LuDevin and more Software Development AgentsThis is an early view of unfinished part of the AI Code Assistant Internals series, if you’re curious about what the recently hyped Devin…·2 min read·Mar 15, 2024----
Wei LuAI Code Assistant InternalsI am working on two serials of experiments, the realtime translation with whisper and the RAG in web browser. ChatGPT and GitHub Copilot…·8 min read·Mar 2, 2024--1--1
Wei LuPerformance of ONNXRuntime WebGPUContinuing the experiment, I compare the performance of wasm and webgpu backends on sentence embedding.8 min read·Feb 15, 2024----