热点
"低精度量化" 相关文章
Microsoft AI Proposes BitNet Distillation (BitDistill): A Lightweight Pipeline that Delivers up to 10x Memory Savings and about 2.65x CPU Speedup
MarkTechPost@AI 2025-10-19T05:39:34.000000Z
How Quantization Aware Training Enables Low-Precision Accuracy Recovery
Nvidia Developer 2025-09-21T15:21:54.000000Z
On Jailbreaking Quantized Language Models Through Fault Injection Attacks
cs.AI updates on arXiv.org 2025-07-08T05:54:12.000000Z
FF-INT8: Efficient Forward-Forward DNN Training on Edge Devices with INT8 Precision
cs.AI updates on arXiv.org 2025-07-01T04:13:54.000000Z
DeepSeekFP8启示：FP4计算让DS成本再降一倍
算力百科 2025-02-15T03:42:02.000000Z
大模型训练开销还能更小！微软推出首个FP4训练框架，训练效果与BF16相当
量子位 2025-01-31T17:09:53.000000Z
大模型训练开销还能更小！微软推出首个FP4训练框架，训练效果与BF16相当
智源社区 2025-01-31T16:52:51.000000Z
大模型训练开销还能更小：微软推出首个 FP4 训练框架，训练效果与 BF16 相当
IT之家 2025-01-30T07:06:39.000000Z