Bhuvanesh Sridharan

Adding distil-whisper model support to TensorRT-LLM

1

## What this PR Does: This PR adds support for converting huggingface's distil-whisper model weights to compatible pytorch `.pt` files which can be further used to build TensorRT-LLM engines. ##...

While streaming with sinks, how does the framework change the positional encodings of the KV cache without having to multiply with the Key and Value matrices?

4

From Section 3.2 in the paper: ``` When determining the relative distance and adding positional information to tokens, StreamingLLM focuses on positions within the cache rather than those in the...

kv_cache_reuse breaking on awq quantized model

2

### System Info - X86_64 - RAM: 30 GB - GPU: A10G, VRAM: 23GB - Lib: Tensorrt-LLM v0.9.0 - Container Used: nvcr.io/nvidia/tritonserver:24.05-trtllm-python-py3 - Model used: Mistral 7B ### Who can...

feat(adapter): rewrite XMLAdapter for nested-data support

11

Closes #8481 ## TL;DR * Replaces regex parsing with `xml.etree.ElementTree`. * Supports nested Pydantic models, repeated tags → `List`, mixed data types. * Keeps all existing flat-structure behaviour (no breaking...