Manickavela

Hi @byshiue, Facing the very same error with same machine config, AWS instance of g5.12xlarge, 4 x A10g GPUs built with cmd from llama example, using llama3 8b model trtllm-build...

Hi, I haven't tried with any Offlinemodel, so I am extending the config support to only for OnlineModel, but easily it can be extended for OfflineModel. Let me know if...

I wanted to keep provider config unique for each models, this would give good control for CUDA and TRT configs, But if developers give different devices(outside of cuda/trt) is a...

> Please have a look at errors reported by `clang-tidy` https://github.com/k2-fsa/sherpa-onnx/actions/runs/9665507110/job/26662771827 > > and the style check by `cpplint`. > > https://github.com/k2-fsa/sherpa-onnx/actions/runs/9665507136 > > (Note: You can run these two...

Python api is having some issues, can you direct me to particular workflowfile to build and test with it

> > Python api is having some issues, can you direct me to particular workflowfile to build and test with it > > Have you fixed it? Sorry for the...

> > what is the cmd to run this? > > > Just start your terminal, activate your python virtual environment, and run > ```bash > pip install clang-tidy >...

Any suggestion for datatype > /home/runner/work/sherpa-onnx/sherpa-onnx/sherpa-onnx/csrc/provider-config.h:30:36: warning: implicit conversion from 'long' to 'int32_t' (aka 'int') changes value from 2147483648 to -2147483648 [-Wconstant-conversion] > int32_t trt_max_workspace_size = 2147483648; > ^~~~~~~~~~

Most of the workflows are failing before build step itself, I think there is a pip dependency issue or something Anyway it is good for review as of now for...

Hi @csukuangfj, Let me know if there is any more suggestions