jamesblonde

This is the beginning of a flight to perceived quality in all things digital and monetary. Fear of losing your money is among the most potent basal human instincts.

I have access to a server with 4 x h200 cards - 540 GB in total memory, but it appears I have to go to 4bit or 3bit even to serve it. Any idea if that is feasible/desirable (we have restrictions that we can't use a chinese model!).

Is this Germany - is there a subsidy included here?

Git was designed with assumptions about local file storage which make it challenge when storing data in a distributed file system. We built our distributed filesystem, HopsFS, to store data in S3. To support high performance git in FUSE, our writes hit remote NVMe disk(s) and asynchronously sync to S3 (you can replicate on NVMes or just do failure recovery). Previously, we used remote NVMe disks as a write-through cache, but that doesn't work with git, S3 latency is too high.

That was my point - it needs to invest its capital in Europe. That will solve its ails.

As Rutger Bergman says about inequality: "it's taxes, taxes, taxes..."

For Europe, it's "capital, capital, capital".

DuckDB's sweet spot is for 'smallish' lakehouses. So, ingestion should not be via duckdb, but rather something like Python/DLTHub for small scale or Spark for large scale or Kafka/Debezium/Flink for streaming data.

For the full weights, unoptimized on vLLM with 2 Nvidia 6000 RTX 48GBs connected by NVLink, i only get 14 tokens/sec with open-code. For batched operations, it climbs to 55 tokens/sec.

For FP8, on a single Nvidia 6000 RTX 48GB, i get 13 tokens/sec on a single GPU and 46 tokens/sec batched.

Sodium-ion batteries are only starting, their price floor in a few years will make solar energy unmatched in price for energy production.

This is the first proof point that the technology is viable - a customer is stumping up big cash.