https://martinuke0.github.io/tags/int8/ Recent content in Int8 on martinuke0's Blog https://martinuke0.github.io/%3Clink%20or%20path%20of%20image%20for%20opengraph,%20twitter-cards%3E https://martinuke0.github.io/%3Clink%20or%20path%20of%20image%20for%20opengraph,%20twitter-cards%3E Hugo -- 0.152.2 en Mon, 21 Sep 2026 09:00:46 +0000 https://martinuke0.github.io/posts/2026-09-21-optimizing-tensorrt-llm-int8-quantization-pipelines-for-real-time-inference-on-multi-gpu-clusters/ Mon, 21 Sep 2026 09:00:46 +0000 https://martinuke0.github.io/posts/2026-09-21-optimizing-tensorrt-llm-int8-quantization-pipelines-for-real-time-inference-on-multi-gpu-clusters/ Real-time LLM inference on multi-GPU clusters demands efficient quantization. This article walks through TensorRT-LLM INT8 pipelines, pipeline parallelism, kernel optimizations, and production-ready deployment patterns.