Rob Meng

Hi, I'd love to have this feature and contribute some code. Could you point me to the necessary components and docs? @annaveronika Thank you!

Looks like to support categorical ONNX export the code need some `ai.onnx.ml.CategoryMapper` nodes? Once all the features are mapped to ints we can just use the `AddTree` path. Is my...

Looks like apex doesn't build this extension by default. https://github.com/NVIDIA/apex/blob/6b7e77b0c34ca2be4243d495423e17d49090b49e/setup.py#L371 https://github.com/NVIDIA/apex/blob/6b7e77b0c34ca2be4243d495423e17d49090b49e/setup.py#L301 adding `--global-option="--fast_multihead_attn"` when installing apex fixed the problem for me. (I'm running pyprof, and I get this exception during...

@salexspb I think this is the bug we are seeing We ran into the same issue. I added debug prints in `__enter__` and `__exit__` of `ConversionHook `. It seems like...

I think this is the same as https://github.com/NVIDIA-AI-IOT/torch2trt/issues/270

A few implementations come mind 1. Inject shell with env override for testing only ```python class Shell: def __init__(..., testing=true, testing_env_defaults={}): self.env_defaults = testing_env_defaults if testing else {} ``` 2....

TL;DR: * Seems to have very little latency impact * We should also test query throughput than just latency. after picking in #960 the difference of index scan performance pre/post...

> is this for scanning or the ANN search? ann search. The bench mark uses `nearest`.

quick note: `object_store` only recently exposed the configurbility of `credentials` field https://github.com/apache/arrow-rs/pull/4235 Going to need to upgrade `arrow-rs` for this one

> Is it because that this is just straight do scanning over memory? > How applicable is https://en.algorithmica.org/hpc/algorithms/argmin/ ? I haven't profiled it. But I think it's mostly becasue our...