rebase: target the official vLLM 0.31.0 release

Use upstream release images at db9527a46873, preserve custom processor conditioning, and include weekly jobs in full Buildkite release validation.

Signed-off-by: tzhouam <tzhouam@connect.ust.hk>

tests/worker_v2/test_capture_query_bound_gpu.py

@@ -46,7 +46,6 @@ def _check_prefill():
     state = OmniModelState.__new__(OmniModelState)
     state.model_config = SimpleNamespace(max_model_len=256)
     state.vllm_config = c
-    state.max_model_len = 256
     state.supports_mm_inputs = False
     with set_current_vllm_config(c):
         group = AttentionGroup(FlashAttentionBackend, ["attn"], spec, 0)