💡 [REQUEST] - please support airllm?
showkeyjar opened this issue · 0 comments
showkeyjar commented
起始日期 | Start Date
No response
实现PR | Implementation PR
https://github.com/lyogavin/Anima/tree/main/air_llm
AirLLM optimizes inference memory usage, allowing 70B large language models to run inference on a single 4GB GPU card.
相关Issues | Reference Issues
No response
摘要 | Summary
would you please support airllm tech? the author said it can optimizes inference memory usage, allowing 70B large language models to run inference on a single 4GB GPU card.
基本示例 | Basic Example
add new
缺陷 | Drawbacks
not known yet.
未解决问题 | Unresolved questions
none yet