Yuchao Zhang
Yuchao Zhang
I have no idea of this line about sampling from softmax. Can you give me a help? ``` sel = tf.one_hot(tf.argmax(logit_probs - tf.log(-tf.log(tf.random_uniform(logit_probs.get_shape(), minval=1e-5, maxval=1. - 1e-5, seed=seed))), 3), depth=nr_mix,...
The doc of [replace-a-response-forwarder-per-method](https://github.com/grpc-ecosystem/grpc-gateway/blob/ee3ef70b7777cde4e61e4e224cb11e92beecee6a/docs/_docs/customizingyourgateway.md#replace-a-response-forwarder-per-method) is not very clear. We cannot directly access the `forward_MyService_Checkout_0` variable outside the generated gw file. If we modify the gw file directly, it will break...
Hi, Thank you for your nice job. But I found that either your FloWaveNet or NVIDIA's WaveGlow has a problem of containing periodic noise.  Maybe this is caused by...
I noticed that libunifex have additional stream design which is currently missing in P2300. However, I have no idea how to parallelize producer and consumer with the current design. What...
https://github.com/polachok/fahrenheit/blob/3f2f13399f37efb4aef1d645ac874ffd13c9a7e1/src/lib.rs#L24 I'm a newbie of Rust and kindly ask why we still need a rc here. For lifetime, it's 'static and is safe to use. For shared ownership, we can...
For example, what's aarnphm/opt-6-7b-quotes here? ``` openllm start opt --model-id facebook/opt-6.7b --adapter-id aarnphm/opt-6-7b-quotes ```
### Feature request Any plan to support nvidia's latest TensorRT-LLM, maybe via triton-inference-server backend? ### Motivation New integration ### Your contribution Test
### Describe the bug FolderBase Dataset automatically resolves under current directory when data_dir is not specified. For example: ``` load_dataset("audiofolder") ``` takes long time to resolve and collect data_files from...