Jamil Brian Palma Salazar

The issue with Llama when trying to create the: checkpoint: does not appear config.json

7

### System Info 2 x NVIDIA Tesla V10016GB vRAM ### Who can help? _No response_ ### Information - [X] The official example scripts - [ ] My own modified scripts...

Issue with token number: how to increase processed input tokens: models llama and phi, with 4 GPUs.

1

### System Info 8 x NVIDIA Tesla V100 ### Who can help? _No response_ ### Information - [X] The official example scripts - [ ] My own modified scripts ###...

How to enable the use of multiple GPUs in the example of the Phi model?

2

### System Info 2 x NVIDIA Tesla V10016GB vRAM ### Who can help? _No response_ ### Information - [X] The official example scripts - [ ] My own modified scripts...

TensorRT v9.2 installation error due to CUDA version. ""-- The CUDA compiler identification is unknown""

1

Hello everyone, I'm trying to install TensorRT version 9.2. I followed the requirements and switched to CUDA 12.2 on a 16GB GPU machine running Ubuntu 20. When I run the...

Echobot - Changing from VMSS to VM or Similar

5

**Describe the issue** The VMSS instances shut down, and this cannot be controlled. **Expected behavior** To prevent them from shutting down, but according to documentation, this cannot be controlled, so...

Echobot, how to make it leave the call

2

**Describe the issue** hello! I would like some help with this, because when I have a group call, the bot joins correctly. After we all leave the call, echobot remains...