Kedar Potdar

icon company NVIDIA icon location Manager, Sys. SW - AI @NVIDIA

Results 10 comments of Kedar Potdar

ModuleNotFoundError: No module named 'tensorrt_llm'

@ryletd Can you please try a fresh install and report back?

feat: can it read repository

Feel free to clone the repos locally and point the application to it!

Enhancement: Support for reading PDFs with partial DRM (AES) - include PyCryptodome dependency

@montge thanks, we will consider this feature request.

Support for Markdown files

Thanks for reporting, we are looking into it.

Missing config/preferences.json and Cookie Handling Errors

Hello, is this an issue with Chat with RTX or the trt-llm-rag-windows repo?

AttributeError: 'WeightOnlyGroupwiseQuantLinear' object has no attribute 'prequant_scaling_factor'

Hello, can you please share the build.py command used for engine generation?

Adding evals after throughput benchmarks

Reviewing from NV side. Please hold on merging till we finish review.

Add DSR1 MTP

I'm not sure the mtp-mode: on actually triggers the dsr1_b200_fp4/fp8_trt_mtp.sh scripts.

Add DSR1 MTP

@kimbochen can you please guide how to add logic in runner/launch b200 to account for mtp flag?

Add DSR1 MTP

Thanks @csahithi . i have made changes accordingly. ran several sample sweeps: https://github.com/InferenceMAX/InferenceMAX/actions/runs/18050118322 https://github.com/InferenceMAX/InferenceMAX/actions/runs/18050505472 https://github.com/InferenceMAX/InferenceMAX/actions/runs/18051017127 https://github.com/InferenceMAX/InferenceMAX/actions/runs/18049715475