ymcki

I am not seeing drastic reduction in speed when compare to 0.5.3 and 0.4.3 using my 4xL40S which has a similar architecture to 4090. But then I am only running...

I created a small dataset with four pod5s that are about 2GB each and run on 4xA100 with 4.3.0 sup model. 5mCG_5hmCG only: 3m49.244s 5mC_5hmC only: 6m21.693s 6mA only: 9m33.237s...

> Hi @ymcki - ack on the limited documentation on our model updates and the version numbers since they can be confusing. We are working on putting something together and...

What about 0.5.0? I am using 0.5.0 now. So far no errors for eight samples.

> Hi @ymcki, > > > Does that mean if force them to run at the same batch size, then I can expect nearly identical basecalls? > > Setting the...

> We will definitely be updating the README here to document this phenomenon. > > @ymcki - can you explain in more detail what you mean by this: > >...

> As a follow up to this, is the same issue seen here expected with the A10 or A30 GPUs? I imagine the answer is no since they utilize the...

> @ymcki Where did you find this? I am unfamiliar with GPUs so went to Nvidia's datasheet for the GPUs...which suggests all three run on the Ampere architecture. https://www.nvidia.com/content/dam/en-zz/Solutions/Data-Center/a10/pdf/datasheet-new/nvidia-a10-datasheet.pdf https://github.com/nanoporetech/dorado/issues/459...

I tried re-running basecalling on the 4xA100. I found that 100% of the reads basecalled are fully identical. That means basecalling is a deterministic process that will 100% reproduce the...

Dear Mike, L4's spec says it supports Tensor Core INT8: https://www.nvidia.com/en-us/data-center/l4/ What do you mean by "it will fall back to FP16"?