awesome-repositories.comBlog

© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com

MCP Blog Curated searches Sitemap Privacy Terms

Fastllm | Awesome Repository

ztxz16fastllm

0

View on GitHub↗

4,779 stars·471 forks·C++·Apache-2.0·0 views

Fastllm

Features

AI & Machine Learning - High-performance large model inference library
LLM Utilities - C++ acceleration library for high-speed model inference.

AI search

Explore more awesome repositories

Describe what you need in plain English — the AI ranks thousands of curated open-source projects by relevance.

Start searching with AI

fastllm是后端无依赖的高性能大模型推理库。同时支持张量并行推理稠密模型和混合模式推理MOE模型，任意10G以上显卡即可推理满血DeepSeek。双路9004/9005服务器+单显卡部署DeepSeek满血满精度原版模型，单并发20tps；INT4量化模型单并发30tps，多并发可达60+。