Connect home devices into a powerful cluster to accelerate LLM inference. More devices means faster inference.
-
Updated
Apr 8, 2025 - C++
#
llama3
Here are 9 public repositories matching this topic...
A high-performance inference system for large language models, designed for production environments.
performance gpu model production cuda efficiency inference transformer llama speculative serving llm llm-inference llama3
-
Updated
Apr 8, 2025 - C++
校招、秋招、春招、实习好项目，带你从零动手实现支持LLama2/3和Qwen2.5的大模型推理框架。
-
Updated
Apr 2, 2025 - C++
Run generative AI models in sophgo BM1684X
large-language-models llm generative-ai chatglm llm-inference llama2 qwen qwen-7b llm-infernece qwen2 qwen1-5 bm1684x llama3
-
Updated
Apr 8, 2025 - C++
Explore LLM model deployment based on AXera's AI chips
transformer vlm edge-computing huggingface llm minicpm qwen2 axera llama3 minicpm-v gemma2 internvl2
-
Updated
Mar 31, 2025 - C++
llama.cpp 🦙 LLM inference in TypeScript
-
Updated
Sep 26, 2024 - C++
Improve this page
Add a description, image, and links to the llama3 topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the llama3 topic, visit your repo's landing page and select "manage topics."