V100s 32GB PCIe ECC Errors

A user who bought a used Tesla V100s 32GB PCIe GPU on eBay for llama.cpp LLM workloads reported a hard crash with uncorrectable ECC errors within a day of use, retiring 32 pages on a card that arrived with zero retired pages. After the crash, the user ran 2 hours of gpu_stress with zero errors and saw no further ECC errors in kernel logs or nvidia_smi over several more days of LLM use, while power-limiting the card to 200W and keeping die temperature below 78C. The user asked whether to return the card, citing inexperience with datacenter GPUs and concern the product will degrade further.

I recently purchased an ebay Tesla V100s 32GB for LLM usage in llama.cpp I power limited it to 200W, and have never exceeded 78C die temp. Within a day of use, I got a hard crash and uncorrectable ECC errors. This event resulted in 32 retired pages. When I received the card, there were zero retired pages. After this event, I ran the card through 2hrs of gpu stress and got zero errors. I have been using it for a few more days with LLM workloads and have seen no further ECC errors in my kernel logs or nvidia smi. Should I return this card? I don’t have enough experience with datacenter GPUs to know if I’m getting ripped off, and the product will degrade further. I appreciate any insights.