rm benchmarking files

add orpheus with trt

add nomic code

modify testing concurrency

update orpheus-tts-streaming

trt-llm config A100 -> H100

move from A100 to H100 default in config.yaml

add max context length

reorg folders

feat: add orpheus tts with streaming (#422)

add orpheus tts

Update config.yaml to add hf-token secret

update docs for deploying via trt-llm

use T4 for sesame

change to L4 for sesame

Add openai tag (#421)

fix lint

add tag

add tag

add refactor of example model input

add chat template deployment

add chat template deployment

mistral 3.1 small (#420)

fix typo

added mistral small 3.1

rm xtts-streaming websocket changes

add sesame-csm-1b example

add qwen-qwq correction + add mixedbread.ai classification model