Paul Hendricks

icon company @NVIDIA icon location Columbus, OH icon location Deep Learning Engineer

Results 19 issues of Paul Hendricks

Add unit tests

Add documentation

Standardize with OpenAIGymAPI.jl for maintainability

Get Travis CI, Appveyor, and Codecov services integrated and working

Write comprehensive unit tests

Create GymClient() function for instantiation; deprecate create_GymClient()

enhancement

Add badges to readme

lora_config shape mismatch when using converted LoRA at runtime

### System Info ## System Info - CPU architecture: x86_64 - Host Memory: 1TB - GPU: NVIDIA A100 80GB x8 - TensorRT-LLM version: v0.18.2 - Triton container: `nvcr.io/nvidia/tritonserver:25.04-trtllm-python-py3` - CUDA:...

bug

bug: changing top_logprobs from u32 to u8 to be consistent with chat

bug: changing top_logprobs from u32 to u8 to be consistent with chat