logo
WangZongwu
The article tags

竹杖芒鞋轻胜马，
一蓑烟雨任平生。

Scroll down
Quantization
Fast On-device LLM Inference with NPUs
  • 04/06
  • 04:59
🔐 本文已加密，请输入密码查看
Efficient GPT-4V level multimodal large language model for deployment on edge devices
  • 03/07
  • 02:28
🔐 本文已加密，请输入密码查看
Anda_ Unlocking Efficient LLM Inference with a Variable-Length Grouped Activation Data Format
  • 02/20
  • 11:04
🔐 本文已加密，请输入密码查看
Bit-slice Architecture for DNN Acceleration with Slice-level Sparsity Enhancement and Exploitation
  • 02/20
  • 11:04
🔐 本文已加密，请输入密码查看
Bridging the Gap Between LLMs and LNS with Dynamic Data Format and Architecture Codesign
  • 02/20
  • 11:04
🔐 本文已加密，请输入密码查看
Ditto_ Accelerating Diffusion Model via Temporal Value Similarity
  • 02/17
  • 06:49
🔐 本文已加密，请输入密码查看
1
Please enter keywords to search
  • to close