RuntimeError: [enforce fail at CPUAllocator.cpp:56]

[Meghana-Meghana]

I am tried the code given under 4. Use BLINK in your codebase. I have set "fast" = True in the config. But, when I execute main_dense.load_models(args, logger=None), I get a following Runtime Error - [enforce fail at CPUAllocator.cpp:56] posix_memalign(&data, gAlignment, nbytes) == 0. 12 vs 0 . With a quick search on the internet, I figured that it is due to insufficient RAM. I am currently using 32 GB RAM. The error occurs at this location while loading the entity encodings.

I would like to know if there is a solution for this problem other than using a high-end RAM.

[ledw]

@Meghana-Meghana Hi, the pre-cached entity file is very big (23G, 6M float vector of dimension 1024), therefore it does not fit in a 32GB RAM. We can try to compress the vectors and upload a smaller version of entity file.

[diegoceccarelli]

So you need more than 32Gb of memory to run BLINK ?

[Meghana-Meghana]

Yes, that is correct.

[seeotter1]

So how much RAM is needed to run it? Is 64 G Tensorbook adequate fo irt?