lab NVIDIA Research · 15h ago · research

FastGen-PDD introduces parallel decoding distillation for fast video and image generation

from English

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.

Compatible with any pre-trained model and supports sampling with varying numbers of function evaluations (NFE).
Learns a representation of mean velocity without regressing its derivative using Jacobian-vector products or finite-difference approximations.
Achieves state-of-the-art performance on LTX-2.3 Text-to-Video/Audio, Wan 14B Text-to-Video, and Qwen-Image Text-to-Image with 4-8 NFE.
Significantly improves generated video diversity compared to existing methods.

PDD offers a scalable alternative for fast inference that avoids mode collapse while maintaining high-quality generation across text-to-video and text-to-image tasks.

Importance 1/3 Trust 3/3 NVIDIA Research Inference efficiency Video generation

Read original

github llama.cpp · just now · 1 view Live

llama.cpp b10984 adds CUDA row-contiguous SUM_ROWS support

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.

github llama.cpp · 1h ago · 1 view Live

llama.cpp b10985 restricts RPC hash-cache to weights

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.

github llama.cpp · 2h ago · 2 views

llama.cpp b10982 adds Vulkan sparse Flash Attention support for DSV4/GLM

The llama.cpp project has released build b10982, which introduces support for sparse Flash Attention via the Vulkan backend. This update specifically targets DSV4 and GLM models, allowing them to leverage sparse attention mechanisms on compatible GPU hardware.

github llama.cpp · 3h ago · 2 views

llama.cpp b10981 fixes stateful decode for Gemma-4 and optimizes GPU MoE inference

The llama.cpp b10981 release addresses critical correctness issues in the OpenVINO backend's stateful decoding path, specifically fixing support for models like Gemma-4 that use per-layer head sizes. It also introduces optimizations for GPU Mixture of Experts (MoE) inference and improves performance through KV state relayouts.

github llama.cpp · 4h ago · 1 view

llama.cpp adds Metal FA kernels for MiniCPM3's HSK=96, HSV=64

The llama.cpp project has added Flash Attention (FA) kernel support for the specific configuration used by MiniCPM3 on Apple Silicon. This change addresses a crash where the `-fa auto` flag would abort due to a missing kernel instantiation for attention key length 96 and value length 64.