A developer's hand-written Gemma 4 port in pure JAX runs across TPU v5e/v6e and NVIDIA T4G GPUs, revealing that while most of the code is portable, two hardware-specific issues break the abstraction. …
A developer detailed the deployment of Google's Gemma 4 2B model on a single Cloud TPU v5e chip using MCP and Antigravity CLI, achieving measured throughput and latency. The v5e chip, at roughly half …
Google's Gemma 4 E2B model serves efficiently on a single TPU v6e chip, achieving 213 tok/s for a single user and scaling to ~2,200 output tok/s across concurrent streams, while its QAT variants fail …
A developer ported Karpathy's nanochat to run on a TPU v6e-8 using JAX, achieving a CORE score that reproduces the original quality but with a model FLOPs utilization (MFU) of about 24%, roughly half …
Google Cloud demonstrated a multi-cluster inference setup deploying an LLM across two regional GKE clusters using TPU v6e accelerators and GKE managed DRANET for networking. The experiment, documented…