Eldar Kurtic

It doesn't work for me, again same error.

@bfineran I have pulled out transfer of masks to the SparseAutoModel class, to avoid repeating a bunch of code for each task. Now, one could enable this feature when adding...

@markurtz makes sense, given that this feature would do the same thing for all models. What do you mean by CLI utility script? The only potential issue I can see...

@markurtz good point about GitHub actions, haven't thought about that one. Then probably better to leave this as it is, and let the users modify their own makefiles if they...

Reopening because the same issue happens at a different place now.

The command for torch-tensorrt installation at [official PyTorch docs page](https://pytorch.org/TensorRT/getting_started/installation.html#installation:~:text=pip3%20install%20torch%2Dtensorrt%3D%3D%3CVERSION%3E%20%2Df%20https%3A//github.com/pytorch/TensorRT/releases/expanded_assets/%3CVERSION%3E) is misleading because it is presented as: ```shell pip3 install torch-tensorrt== -f https://github.com/pytorch/TensorRT/releases/expanded_assets/ ``` implying that you need to type...

yes, with `name: hf_causal_lm` I've been able to reproduce most of the results in the blog (modulo some small diffs) except for Jeopardy and MMLU, where I see a bit...

@bfineran that's a very good point for multiple modifiers, I've completely missed it. Regarding logging only when `global_sparsity` is True: - from practical point of view, I think it would...

You need `/usr/local/go/bin` to run `go get ...` command. After that, it is going to use your env variable `GOPATH` to find binary for command `drive init`, `drive pull` and...

@sameerreddy13 I am having the same issue, would you be able to share the diffs for "dropped in the new flash attention module and it works without a hitch"?