更多精彩内容，关注钛媒体微信号（ID：taimeiti），或者下载钛媒体App
说到底，没有商业闭环的开发之路，注定是脆弱且难以为继的。软件开发从来都不是孤立的技术创作，从产品研发、市场推广，到变现盈利、迭代优化，每一个环节都不可或缺，这恰恰是伊朗开发者最缺失的东西。
。91视频对此有专业解读
�@�����̃v���[���g�ł́A�b���ƂȂ����u�S�[���h�v�J�[�h�t�F�C�X�̑��A�u�ԑ��v�J�[�h�t�F�C�X�������܂��B2���ނ������ɑ��悳�ꂽ�������A�ԑ��t�F�C�X�̕��͂��܂��C�t�����Ă��Ȃ��悤�ł��B���������������ŁA���������܂��B
Abstract:Autoregressive decoding is bottlenecked by its sequential nature. Speculative decoding has become a standard way to accelerate inference by using a fast draft model to predict upcoming tokens from a slower target model, and then verifying them in parallel with a single target model forward pass. However, speculative decoding itself relies on a sequential dependence between speculation and verification. We introduce speculative speculative decoding (SSD) to parallelize these operations. While a verification is ongoing, the draft model predicts likely verification outcomes and prepares speculations pre-emptively for them. If the actual verification outcome is then in the predicted set, a speculation can be returned immediately, eliminating drafting overhead entirely. We identify three key challenges presented by speculative speculative decoding, and suggest principled methods to solve each. The result is Saguaro, an optimized SSD algorithm. Our implementation is up to 2x faster than optimized speculative decoding baselines and up to 5x faster than autoregressive decoding with open source inference engines.
更多精彩内容，关注钛媒体微信号（ID：taimeiti），或者下载钛媒体App