Feature: Add Qwen3-VL-8B-Instruct to the qwen_vl family

Summary

Extend the qwen_vl family's existing Qwen/Qwen3-VL-2B-Instruct support to
Qwen/Qwen3-VL-8B-Instruct.

Why

Both checkpoints share the same architecture class
(Qwen3VLForConditionalGeneration, model_type: qwen3_vl) and only differ in
scale:

families/qwen_vl/config.py reads these dimensions from the checkpoint's own
config.json rather than hardcoding the 2B shape, so this is expected to be a
scale-up within the existing family rather than a new architecture.

Apache-2.0, ~19.7M downloads on Hugging Face.

Plan

• Add a manifest + test case for Qwen/Qwen3-VL-8B-Instruct under
  families/qwen_vl/tests/manifests/.
• Build and run the real GPU E2E (native generate / VL-inference CLI path)
  against the pinned checkpoint revision.
• If the 8B checkpoint needs tensor-parallel to fit comfortably, evaluate
  qwen_vl's existing TP builder path (already used for
  Qwen/Qwen2.5-VL-3B-Instruct).
• No shared-file changes expected (no new task type, no new CLI surface) —
  should stay entirely inside families/qwen_vl/.

Non-goals

Quantized precisions, additional Qwen3-VL sizes beyond 8B, streaming
generation.

Start in families/qwen_vl/config.py and inspect the existing manifest and tests under families/qwen_vl/tests/manifests/, especially the Qwen3-VL-2B-Instruct case. Add the 8B manifest and test, then build and run the pinned-checkpoint GPU E2E through the native generate or VL-inference CLI path. If it does not fit comfortably, evaluate the existing tensor-parallel builder path; done means the real E2E passes.