gaoteng-git

Is there "trained" model?

7

Since it costs a long time training (30hours on GPU) to get the smart model, would you please provide an already trained model file that I can run without training...

libuv backend not ready for use?

1

I change the gloo/examples/example1.cpp from using "tcp" to "uv". However, it fails at Pair::createSendBuffer in gloo/transport/uv/pair.h. This function is not implemented and only has "abort()" in it. I find that...

Is there any plan to support running on Windows?

1

Hello! I have a rough view of the gloo code. It seems only support running on Linux. Because one of the underlying transport module "libuv" is cross-platform, how big is...

Is any plan to support Dual Chunk Attention (DCA)?

1

[DCA ](https://arxiv.org/html/2402.17463v1) is an effective method to run long input context inference. Does TensorRT-LLM plan to support this feature?