HSLUCKY

've identified the root cause. It's due to Outliens creating a massive cache object during FSM initialization. Despite our server utilizing 77G VIRT MEMORY, the process didn't terminate, ultimately leading...

After removing the "maxLength": 2048 parameter, apart from the initial slow loading, subsequent executions are able to locate the cache and infer results immediately. {"type": "string", "maxLength": 2048}

def __init__(self, regex_string: str, tokenizer): @cache() def create_states_mapping( regex_string: str, cacheable_vocabulary: Tuple[Tuple[str, int], ...] ) -> Tuple[dict, set]: """Create the variables related to the mapping between states and tokens The...

Can you leverage the GPU to generate the cache for improved speed and address the bug causing the generation of excessively large cache indices?