harmansingh4163-ai/ESP-32-s3-Story-maker-LLM

15M/42M-param Llama split across two ESP32-S3s over 3 wires — too big for either chip alone. INT4, flash mmap, bit-exact verified.

语言：C · GitHub 星标：17 · Fork：1

话题：embedded-distributed-inference · esp32-s3-llm · llama2 · pipeline · quantization · tinyml-esp32

在 GitHub 上查看原仓库