ollama Lava13b内存访问故障在api/聊天(第一次调用正常,第二次失败)

zu0ti5jz  于 2个月前  发布在  其他
关注(0)|答案(2)|浏览(26)

我有两个x7900tx显卡。如果我在每次请求后关闭ollama,并指定只使用1个GPU,它运行得很好。我尝试了8次运行ollama服务器,在每次请求后关闭,在某个时刻它也崩溃了,因为关闭并没有清除显存。

d8tt03nd

d8tt03nd1#

played with #2146 keepalive parameter to 0 and had no more success (some vram still not free after shutdow from the keepalive).
tried today with same os, gpu on my desk with only 1 gpu and working like a charm so I suggest search arround the 2 gpu memory management, also noticing the vram going in the 2 gpu but 24gb vram cards and only 4-8 gb models

cl25kdpy

cl25kdpy2#

翻译结果为:这次又遇到了,但在梅尔塔风(Mistral)上,所以这个问题与2xGPU相比,与Lava的关系更大(经过几次尝试后发生)

$x_1^c_0^d_1^x$

相关问题