What changed
Google integrated TPU support for Qwen3 text and multimodal embedding workloads into vLLM, including tensor alignment, JAX and XLA pre-warming, and a StepPool path that preserves pooling state through chunked prefill and request preemption. Public GKE and AI Hypercomputer recipes cover 8B text and vision-language checkpoints.
Why it matters
Embedding services can now use a common open serving engine across TPU and other accelerators while testing long-context numerical parity. The public recipes make the serving claim reproducible instead of leaving it as a managed-platform promise.
What to do
Run the published Qwen3-Embedding-8B recipe on one representative retrieval corpus. Compare vector parity, recall, throughput, cold starts, preemption recovery, autoscaling, accelerator fallback, and total query cost against the current GPU deployment.
Caveat
The throughput and parity results are Google-run on selected Qwen3 workloads. They do not establish price-performance across models, Regions, traffic shapes, quantization settings, retrieval quality, or failure modes, and the example enables remote model code.