feat: support flash attention 2 in qwen2 vl vision blocks

[drbh]

This PR adds support for flash attention within the vision blocks of qwen2vl. This improves latency and reduces spikes in memory usage from sdpa attention (helps avoid oom'ing on large images).

running

text-generation-launcher --model-id Qwen/Qwen2-VL-7B-Instruct

on a single L4's with a small model this has a ~5% perf improvement: prev: ~67ms per token current: ~63ms per token.

ps** it's likely the performance improvement scales with the size/number of layers however I have not benchmarked any larger models to measure the difference.