Gemini 3.8 Flash benchmarked so fast the engineer thought his Slurm job crashed
_lewtun · x · 2026-09-25
Hugging Face engineer Lewis Tunstall praised Google's serving infrastructure: while benchmarking Gemini 3.8 Flash on a new eval, it ran so fast he assumed his Slurm job had crashed — an anecdotal signal of the model's notably low inference latency.
More from Infra
- Altman says OpenAI aims to replace Nvidia in the medium to long term — zephyr_z9 · 2026-11-11
- Chinese University Bought Nvidia H200 Chips Despite US Blacklist — pstAsiatech · 2026-11-11
- vLLM Crosses 4,000 GitHub Contributors on Its Inference Engine — NVIDIAAI · 2026-11-11
- Baidu's ERNIE Evolve tops public bests on NanoGPT Speedrun, brings RSI to real inference optimization — xiaohu · 2026-11-11
- Baidu says RSI auto-optimized ERNIE inference, 6.24x decode speedup on Kunxin P800 — xiaohu · 2026-11-11
- Nvidia's supply commitments jump from $119B to $279B in one quarter, locking up 2027-28 memory — tengyanAI · 2026-11-11