Pedro Valois comments

Results 17 comments of


                                            Pedro Valois

Batch Inference with Llama 3.2 Generate Function: Only the First Result is Correct

I also need batch inference. Any update on this?

bug: async ingest doesn't work for multiple repos

LMK if you need help and we could open a PR

bug: async ingest doesn't work for multiple repos

Thank for the positive response. @dmnunez1993 can you open the PR?

Feature: Does lanceDB have plans to support ForeignKey?

Any plan for adding it this year?

BatchedInferencePipeline missing in PyPi release

Thank you for the info. Do we have an ETA for next release?

Does anyone konw the average speed or time to recognize a single image when using RTX 4090 20gb+?

I am not sure about the cost, but on my 4090, I am getting lifetime avg 522 tks/s (although it fluctuates around 400tks/s - 600tks/s).

[FEA] Byte Pair Encoding Tokenizer

Is there any update on this? I am looking into pre tokenizing 100Tb of data for NeMo / Megatron and was trying to look for alternatives to HF tokenizers.