Venky

test(perf): Add some `Llama-3_3-Nemotron-Super-49B-v1` integration-perf-tests (TRT flow, trtllm-bench)

33

# Description - Add some `Llama-3_3-Nemotron-Super-49B-v1` integration-perf-tests (cpp backend, trtllm-bench). - This also exposes a `--trust_remote_code` flag in the `trtllm-bench-build` subcommand, that is required for `transformers` library to use Autoclasses...

# Expand PyT `llama_v3.1_nemotron_nano_8b` perf tests coverage ## Description This PR adds end-to-end performance results for the **llama_v3.1_nemotron_nano_8b** bfloat16 engine on 1 H100. Two broad load patterns were evaluated on...

[TRTC-1965] [feat] Add config db and docs

3

## Description - [x] Clean #9272 schema and rebase this PR on top - [x] Include config db packaging - [ ] Reflect #9104 in docs - [x] Add script...

[TRTC-1943][feat] Env vars override support in LLM API

91

## Description ### Context for reviewers: * Currently to get optimal deployments, we expect user to specify an optimal `extra_llm_api_options` yaml file as well as the right env vars (like...