1
一次吃下一本书！百度开源新OCR，作者疑似前DeepSeek研究员
百度开源新OCR技术突破“一次性”处理整本书，前DeepSeek研究员打造，显存占用几乎不增长。
2
xKV: Cross-Layer KV-Cache Compression via Aligned Singular Vector Extraction
提出跨层KV-Cache压缩新方法xKV，利用对齐奇异向量提取大幅减少显存占用，加速大模型推理。
arXiv:2503.18893v2 Announce Type: replace-cross Abstract: Long-context Large Language Models (LLMs) enable powerful applications but incur high memory…
3
Gemma 4: The 128K Multimodal Powerhouse in Your Terminal
揭秘长上下文推理的内存陷阱：即便模型量化后塞入显存，注意力KV缓存也可能比模型本身更吃内存。
A raw, developer-first look at Google’s new open-weight Gemma 4 family—featuring a hands-on local Python setup, a comparison of the 2B, 9B, and 31B va…