DxP

yes I tried to reproduce and failed on : import milvus part of the code even if I downgraded pymilvus to older version on python 3.11 . its weird and...

thank @jshook . Sorry being newbies here do you mean it is not disabled now and okay to use ? I tried to launch this using nb5 : nb5 run...

@MarkReedZ which machine this benchmark is running for ? Intel Bf16 should show better results on 4th Gen Sapphire Rapids (SPR) with AMX accelerators enabled because BF16 supposed to show...

So far I know Genoa has no BF16 support as at this moment it works on Intel SPR with AMX acceleration only

@ashvardanian we have tested two matrix with inner product and Before use of AMX Inner product we runtime used Intel oneDNN to reorder F32 data to BF16 . Certain dataset...

> Feel free to contribute the AlloyDB client for test and share the performance with us~ Sorry if the ask is misunderstood. I am not asking about contribution . Since...

And perhaps JVector from Cassandra / Datastax too ?