ended7월 30일· 1 sources
One TPU Chip, Eight Agents: Serving Small Agent Workloads with Raw JAX
Why it matters
Cloud TPU v6e-1 (ct6e-standard-1t , one v6e chip, 32 GB HBM), GCE flex-start, europe-west4-a. vLLM baseline measured 2026-07-21. The workload nobody benchmarks Serving benchmarks optimize for the wron...
1
Sources
+0
24h
—
Growth
7d
Active