AI Coding Live News

Diffusion Transformers (DiTs) underpin frontier video generation systems and high-fidelity 3D modeling, yet self-attention computation over extreme sequence lengths introduces prohibitive inference latencies and memory bottlenecks. While sparse attention represents a promising acceleration pathway, existing methods suffer substantial visual quality degradation and texture corruption under high sparsity regimes. Researchers from The Chinese University of Hong Kong (CUHK) and ByteDance analyze sparse attention failures in DiTs (arXiv:2610.06801), tracing quality drops to three root causes: rigid token grouping constraints, inaccurate interaction selection, and uncompensated attention residuals from discarded tokens. The authors introduce Meta-Cached Sparse Attention (MC-Sparse, project site: dodododddo.github.io/mcsparse-project-page/), a training-free framework that preserves individual Key-Value (KV) selection precision while organizing similar Queries into tile-aligned blocks for hardware efficiency on GPUs. MC-Sparse caches query clusters, exact KV indices, and dense-sparse attention output residuals, reusing this metadata across downstream denoising timesteps. On Minimax-H3-Base video models, MC-Sparse delivers a 1.80x denoising speedup, and a 2.32x acceleration on 3D generative backbones, maintaining near-identical fidelity to dense attention with zero visible quality degradation.

Long-horizon LLM agents accumulate expanding interaction histories that saturate GPU KV-cache memory and choke self-attention throughput. While sparse attention algorithms mitigate these bottlenecks mathematically, existing production serving engines (e.g. vLLM) are tightly coupled to dense tensor layouts, preventing heterogeneous sparse mechanisms from sharing infrastructure. Researchers from Harbin Institute of Technology (HIT) release SparseEngine (arXiv:2609.39068), an open-source, sparse-first inference engine built from the ground up for long-horizon agent workloads. SparseEngine establishes a shared lifecycle contract enabling 15 diverse sparse attention methods across four distinct families to control their custom KV representations while unifying memory management. It introduces Chain Cache to resume stateful KV-evicted contexts across multi-turn requests and Controllable Prefix-Cache Pruning to discard stale history without disrupting prefix matching. Empirical evaluations on long-horizon agent benchmarks show that SparseEngine delivers over 10x higher throughput under KV eviction, over 2.5x faster decoding throughput than vLLM at matched concurrency, and more than 2x end-to-end task speedups with zero degradation in model reasoning accuracy.

Alibaba Qwen released open-weight Qwen3.8-Flash, a multimodal Mixture-of-Experts model billed as an early preview of the Qwen4 architecture. The production-scale checkpoint is 125B parameters plus 51B N-gram embeddings, with only 6B activated per token. The new stack combines Gated DeltaNet plus Qwen Sparse Attention, Gated Residual branches, N-gram embeddings that can live in host memory, and a refined Muon optimizer. Qwen said it trained at about one-ninth the cost of Qwen3.7-Plus while beating it across the board, especially on coding and office work: 58.7 on DeepSWE 1.1, 62.5 on SWE-bench Pro, 73.9 on CoWorkBench, 84.5 on AndroidWorld, and 95.7 on MathVision with CI. Native context is 262K tokens, extendable to 1M with YaRN; at 1M context the QSA kernel is up to 7.6x faster in prefill and 4.9x faster in decode. QwenCloud lists roughly $0.15 input / $0.47 output per million tokens, and day-0 runtimes arrived from NVIDIA NeMo, SGLang, Unsloth, OpenRouter, and OpenCode Go.