QuantWM: Temporally Consistent 2-Bit KV Cache Quantization for Video World Models
QuantWM applies training-free 2-bit KV cache quantization to video world models while preserving temporal consistency.
42
AI model
LongCat-Video
- Mentions · 7d0
- Mentions · 30d0
- All mentions3
- First seenSep 13, 2026
- Last mentionedSep 27, 2026
Timeline
3 articles · newest firstNunchux 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.
30
VC-Attention: Value Smoothing and Softmax Casting for Low-bit Attention
VC-Attention is a training-free low-bit attention method for diffusion transformers, achieving 1.46-1.59x kernel speedups on datacenter GPUs with higher fidelity.
38
Appears with
- HunyuanVideo-1.5ai model · 2
- MiniMax-H3ai model · 2
- VC-Attentionproduct · 2
- NVIDIAvendor · 1
- FlashAttention-4product · 1
- Matrix-Game-2ai model · 1
- LingBot-World-v2ai model · 1
- Causal-Forcingai model · 1
- ExpCast-FP8product · 1
- Wan2.2ai model · 1
- Wan2.2-T2V-A14Bai model · 1
- HY-World 1.5ai model · 1
- V-Smoothproduct · 1
- Nunchux AIvendor · 1
- SageAttention3product · 1
- SageAttention2product · 1
Entities are extracted by the model from each article. First seen , last mentioned . Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.