OpenAI@OpenAI部署后，我们应用 GPT-5.6 Sol 通过让自身运行更高效来推进效率前沿。 结果： - 生产 GPU 内核改进使服务成本降低 20%。 - 改进的推测解码使 token 生成效率提升 15% 以上。
After deployment， we applied GPT-5.6 Sol to advance the frontier of efficiency by making itself more efficient to run.
The results： - 20% lower serving costs from production GPU kernel improvements. - 15%+ better token-generation efficiency from improved speculative decoding.
部署后，我们应用 GPT-5.6 Sol 通过让自身运行更高效来推进效率前沿。 结果： - 生产 GPU 内核改进使服务成本降低 20%。 - 改进的推测解码使 token 生成效率提升 15% 以上。
After deployment， we applied GPT-5.6 Sol to advance the frontier of efficiency by making itself more efficient to run.
The results： - 20% lower serving costs from production GPU kernel improvements. - 15%+ better token-generation efficiency from improved speculative decoding.