fastllm - 纯c++的全平台llm加速库. ztxz16 August, 2023. original-date: 2023-05-13T08:32:51Z
fastllm - 纯c++的全平台llm加速库 [link]Paper  abstract   bibtex   
纯c++的全平台llm加速库,支持python调用,chatglm-6B级模型单卡可达10000+token / s,支持glm, llama, moss基座,手机端流畅运行
@misc{ztxz16_fastllm_2023,
	title = {fastllm - 纯c++的全平台llm加速库},
	copyright = {Apache-2.0},
	url = {https://github.com/ztxz16/fastllm},
	abstract = {纯c++的全平台llm加速库,支持python调用,chatglm-6B级模型单卡可达10000+token / s,支持glm, llama, moss基座,手机端流畅运行},
	urldate = {2023-08-28},
	author = {ztxz16},
	month = aug,
	year = {2023},
	note = {original-date: 2023-05-13T08:32:51Z},
	keywords = {\#Code, \#Github, \#LLM, /unread},
}

Downloads: 0