Hugging Face
Search models, datasets, users...
Ctrl K
Models
Datasets
Spaces
Buckets
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
Parakon
/
parakon-runtime
Like
0
Follow
Parakon
3
parakon
llama.cpp
cuda
compression
License:
parakon-community-license
Model card
Files
Files and versions
xet
Community
Copy to bucket
main
parakon-runtime
/
tools
/
batched-bench
14.1 kB
Ctrl+K
Ctrl+K
1 contributor
History:
1 commit
kat0012
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 7)
d2816aa
verified
2 months ago
CMakeLists.txt
Safe
745 Bytes
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 7)
2 months ago
README.md
Safe
3.54 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 7)
2 months ago
batched-bench.cpp
Safe
9.73 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 7)
2 months ago
main.cpp
Safe
131 Bytes
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 7)
2 months ago