Show HN: FusionHarness – An Open-source Mixture-of-Agents compound-model servergithub.com5 ポイント·投稿者 jackxlau·25 日前·1 コメント
jackxlau·28 日前·議論In my own testing I have seen peak performance happen usually within 15-20% of the intended context limit, albeit there are a few optimizations depending on the task quality.
jackxlau·先月·議論the handshake process to unlock the A100 cores is pretty interesting it reminds me of driving CPU cores like a GPU command queue.
jackxlau·先月·議論I came across the conclusion here since a change sometimes spans several repos, per-repo history optimizes the wrong target.