Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
neural-nova
/
Llama-3.1-8B-Instruct-optimized
like
0
Follow
neural nova
4
cuda
custom-kernels
inference-optimization
llama
License:
llama3.1
Model card
Files
Files and versions
xet
Community
Copy to bucket
new
main
Llama-3.1-8B-Instruct-optimized
1.42 MB
Ctrl+K
Ctrl+K
1 contributor
History:
2 commits
Khanin Udomchoksakul
Add optimized CUDA kernels (RMSNorm, MLP, Attention) and patched Llama-3.1 modeling file
6f657bb
verified
4 days ago
kernels
Add optimized CUDA kernels (RMSNorm, MLP, Attention) and patched Llama-3.1 modeling file
4 days ago
patched_transformers
Add optimized CUDA kernels (RMSNorm, MLP, Attention) and patched Llama-3.1 modeling file
4 days ago
.gitattributes
1.84 kB
Add optimized CUDA kernels (RMSNorm, MLP, Attention) and patched Llama-3.1 modeling file
4 days ago
README.md
5.36 kB
Add optimized CUDA kernels (RMSNorm, MLP, Attention) and patched Llama-3.1 modeling file
4 days ago
requirements.txt
Safe
126 Bytes
Add optimized CUDA kernels (RMSNorm, MLP, Attention) and patched Llama-3.1 modeling file
4 days ago
