Packing multiple questions into one forward pass saves compute but adds instability

antoine_chaffin · x · 2026-10-17

The author describes packing multiple questions about the same state into a single fully bidirectional forward pass: all questions share one sequence, each with its own readout marker. With a single question this is equivalent to v1.1; with multiple questions the shared state acts like a cache, and Qwen's architecture supports very long multi-question inputs.

He also notes the downsides: the resulting decision depends on which questions get packed together, making it less stable across runs if the packing varies, and potentially harmful when packed questions conflict with each other.

Related event: pplx-decider Packs Multiple Questions into One Forward Pass with Shared State(2 posts)→

Original post →

More from Research

Research channel →