两张4090卡上部署rerank模型，无法并行计算

[yidasanqian]

asyncio并发跑600份文档rerank，还是单卡100%负载，另一张卡0%，请问是否需要特别的配置？

[qinxuye]

replica（副本） 配置成2.

[yidasanqian]

副本是2，为什么gpu索引不是显示0，1？

[yidasanqian]

@qinxuye reranker.xinference_rerank:_rerank_batch:77 - rerank response text: {"detail":"Model actor is out of memory, model id: bge-reranker-v2-m3-1, error: CUDA out of memory. Tried to allocate 2.00 GiB. GPU 0 has a total capacity of 23.55 GiB of which 848.44 MiB is free. Process 159 has 0 bytes memory in use. Including non-PyTorch memory, this process has 0 bytes memory in use. Of the allocated memory 19.13 GiB is allocated by PyTorch, and 525.93 MiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation. See documentation for Memory Management (https://pytorch.org/docs/stable/notes/cuda.html#environment-variables)"}

怎么配置xinference以避免出现oom

[qinxuye]

你是两张卡吗？配置 replica 2 就行，不需要配置 gpu idx。

[yidasanqian]

你是两张卡吗？配置 replica 2 就行，不需要配置 gpu idx。

不止两张

[qinxuye]

目前多个 replica 还不能指定 gpu idx。

要限制 XInf 的使用可以启动的时候指定 CUDA_VISIBLE_DEVICES 。

[Minamiyama]

是不是可以开多个docker xinf服务实例，每个实例分配一个device idx🤣

[qinxuye]

后续要让 worker_ip 和 gpu_idx 支持多副本/分布式推理。还在设计。

[jiliangqian]

你是两张卡吗？配置 replica 2 就行，不需要配置 gpu idx。

我是两张卡，怎么部署多个replica >2 模型在一张卡上?

[github-actions[bot]]

This issue is stale because it has been open for 7 days with no activity.

[github-actions[bot]]

This issue was closed because it has been inactive for 5 days since being marked as stale.

[3leg0ocat]

请问有解决吗？我配置了 replica 2，还是会报同样的错误，显示单卡显存不足。