# ztxz16/fastllm — RepoVerse

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+。

URL: https://repoverse.app/cards/640177564

[Repository source](https://github.com/ztxz16/fastllm)

## Card snapshot

- Edition: Genesis
- Rarity: uncommon
- Finish: Base
- Attack: 5534
- Defense: 3979
- GitHub stars: 5114
- GitHub forks: 503
- Language: C++
- Category: Programming Languages
- Snapshot date: 2026-10-22

These repository statistics and game attributes belong to this dated card snapshot. They are not a current assessment of software quality.

This page describes the repository card, without a holder or individual copy record.

- [Rules](https://repoverse.app/rules.md)
- [Explore](https://repoverse.app/explore)