20:34
2026-08-03
twitter.com
artificial-intelligence
DeepSeek-V4-Flash 2.98x faster on 4x B200, lossless
RunInfra AI optimized DeepSeek-V4-Flash-0731, achieving a 2.98x speedup on 4x B200 GPUs, with median latency reduced from 9248 ms to 3095 ms and throughput increased from 113 to 363 tokens per second,…