是否支持多卡推理或LORA?
Chineselock opened this issue · comments
Chineselock commented
您好,能否调整API使模型推理时存储在多张显卡上?我现在有多张24G显存的显卡并且我希望能够运行LLama-7B进行embedding
Train and Infer Powerful Sentence Embeddings with AnglE | 🔥 SOTA on STS and MTEB Leaderboard
Chineselock opened this issue · comments
您好,能否调整API使模型推理时存储在多张显卡上?我现在有多张24G显存的显卡并且我希望能够运行LLama-7B进行embedding