Researchers introduce Parallel Decoding Distillation (PDD), a simplified trajectory-based method to accelerate inference in diffusion and flow matching models. Unlike current approaches that rely on hard-to-optimize variational score distillation and adversarial losses, PDD predicts multiple denoising steps per network evaluation.
Nvidia researcher N. Horrocks introduces extended detector error models (EDEMs) designed to handle fault-tolerant quantum programs with stabilizer circuits and stochastic Pauli faults. These models allow error analysis to compose in sequence and parallel, mirroring the structure of physical circuit realizations.
Anthropic released Claude Code v2.1.271, introducing fast mode for Remote sessions, mouse support in the fullscreen config panel, and stricter per-command domain controls for sandboxed auto mode.
The llama.cpp project released version b10984, introducing CUDA support for row-contiguous SUM_ROWS operations. This update also organizes the code to include GGML_OP_MEAN for handling row-contiguous tensors via a shared kernel.
The llama.cpp project released build b10985, which modifies the RPC backend to limit hash-based caching exclusively to weight tensors. This change addresses an issue where activation data was unnecessarily hashed and stored, leading to excessive disk usage.