ZeroHour

Search: “kernel 3”

2 stories in the last 24h

DeepSeek-v4.1 Flash: Pushing the Limits of KV Cache Compression

DeepSeek-V4.1 Flash is a 552B-parameter multimodal MoE model with 1M-token context achieving 4x KV cache compression for long-horizon agent workloads.

A detailed analysis of the DeepSeek-V4.1 Flash technical report describes a 552B-parameter multimodal mixture-of-experts model supporting contexts up to 1 million tokens. Its Causal Encoder-Decoder (CED) architecture activates 8B parameters during prefill and 16B during decode, and reportedly delivers about 420 tokens/s. Joint optimization of architecture (CSA2 cross-layer compression), FP4 KV cache precision, and deployment strategy cuts runtime KV cache to roughly 1/4 and persistent KV cache to about 1/8 of DeepSeek-V4-Flash at the same sequence length, targeting storage and bandwidth bottlenecks in long-horizon agent serving. The author notes all DeepSeek-V4 Pro models were taken offline following the release.

Nunchux AI Introduces VC-Attention: A Training-Free Low-Bit Attention Kernel That Speeds Up Video Diffusion Transformers

Nunchux AI introduces VC-Attention, a training-free low-bit attention kernel that speeds up video diffusion transformers up to 3.58x.

Nunchux AI unveiled VC-Attention, a training-free attention kernel for video Diffusion Transformers combining V-Smooth (k-means value-token grouping with block-mean residual quantization) and ExpCast-FP8 (single multiply-add softmax exponentiation). Benchmarks on Wan2.2-T2V-A14B, LongCat-Video, HunyuanVideo-1.5, and MiniMax-H3 show 1.59x attention speedup on B200 at 8-bit and 3.58x on RTX 5090 at 4-bit, with end-to-end gains up to 1.70x. It beats SageAttention2 by 2.3 dB PSNR on Wan2.2 at 8-bit and SageAttention3 by up to 3.6 dB at 4-bit. No public kernel release yet; a proprietary extension runs in Nunchux's stack.

MarkTechPost · 7h agoAI research 2 sources1