Michal Guzek

[TRTLLM-4932] Add CLI accuracy tests for Llama-3_3-Nemotron-Super-49B-v1 and LLM API FP8 variant

8

## Description Add CLI accuracy tests for Llama-3_3-Nemotron-Super-49B-v1 and LLM API FP8 variant. CLI accuracy tests are still needed because NIMs use TRT-LLM's TRT backend for now. ## Test Coverage...

## Description Add CLI accuracy tests for Llama-4-Scout-17B-16E-Instruct. CLI accuracy tests are still needed because NIMs use TRT-LLM's TRT backend for now. ## Test Coverage ## GitHub Bot Help `/bot...

[TRTLLM-4932] Add CLI accuracy tests for Llama-3.3-70B-Instruct and LLM API BF16 variant

16

## Description Add CLI accuracy tests for Llama-3.3-70B-Instruct and LLM API BF16 variant. CLI accuracy tests are still needed because NIMs use TRT-LLM's TRT backend for now. ## Test Coverage...

[TRTLLM-4932] Add QA accuracy tests for NIM-prioritized models

12

New tests added: - Llama-3.2-1B: added mmlu benchmark - Llama-3.1-Nemotron-Nano-8B-v1: added GSM8K, GPQADiamond benchmarks - Llama-3_1-Nemotron-Ultra-253B-v1: added the entire model (FP8 variant is being added to `ftp/llm-models`) - Phi-4-mini-instruct: added...