Feed Entities Podcasts Deep Dives Developers About

[KongchangAI]

Real-time AI knowledge base. Every claim is traceable to its source, with data freshness under 24 hours.

Powered by 240+ first-hand AI sources

Knowledge

Feed
Hot Entities
Podcasts

Developers

CLI
MCP Server
REST API
About

© 2026 KongchangAI. The freshest, most accurate AI knowledge

Unverified50% confidenceBenchmarkExact time

GGUF 现已支持张量并行（Tensor Parallelism），可带来约 +30% 的推理吞吐提升

1

Sources

50%

Confidence

Medium-term (~90 days)

Relevance

7/7/2026

First Seen

Valid until: 10/5/2026

Sources

Unsloth重磅更新：支持DiffusionGemma与Gemma 4 MTP，推理速度提升2倍

rss6/13/2026

Related Claims

UnverifiedTensorRT-LLM专门为Blackwell引入了FP4量化推理路径，并针对Blackwell的新型Tensor Core单元重写了GEMM内核54% similar UnverifiedMuon优化器由Kosson等研究者提出，核心改进在于对梯度更新矩阵进行正交化处理53% similar Unverified双线性池化方法约在2015年前后出现，是FGVR的重要里程碑，通过两个特征网络输出的外积捕捉二阶统计关系53% similar Unverified支持向量机（SVM）由 Vapnik 等人在 1990 年代提出，通过核函数将低维线性不可分问题映射到高维空间求解52% similar Unverified动态计算图相比早期TensorFlow静态图是PyTorch在研究社区迅速普及的根本原因52% similar

Cite This Claim

Stable URI

https://kongchang.com/claim/172710

API

curl https://kongchang.com/api/v1/knowledge/claims/172710

MCP

get_claim(id=172710)