Hugging Face's logo

nm-testing
/
Llama-3.1-8B-Instruct-QKV-Cache-FP8-Per-Tensor

Transformers
kv-cache
fp8
Model card Files
xet
Community
Llama-3.1-8B-Instruct-QKV-Cache-FP8-Per-Tensor
File size: 143 Bytes 
76b4488
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
 
---
library_name: transformers
tags:
  - kv-cache
  - fp8
---

# Llama-3.1-8B-Instruct-QKV-Cache-FP8-Per-Tensor

Empty model card placeholder.