Hugging Face
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
Spaces:
mrfakename
/
flint
Like
3
Running
on
Zero
App
Files
Files
Community
Fetching metadata from the HF Docker repository...
main
flint
62.5 kB
Ctrl+K
Ctrl+K
1 contributor
History:
3 commits
mrfakename
Faster inference: CUDA-graph decode, Triton MoE decode, flash attention with sinks, grouped-GEMM MoE prefill
09101a6
verified
10 days ago
.gitattributes
Safe
1.52 kB
initial commit
10 days ago
.gitignore
Safe
19 Bytes
Flint chat demo
10 days ago
README.md
Safe
1.03 kB
Flint chat demo
10 days ago
app.py
Safe
9.85 kB
Faster inference: CUDA-graph decode, Triton MoE decode, flash attention with sinks, grouped-GEMM MoE prefill
10 days ago
flint.py
Safe
49.9 kB
Faster inference: CUDA-graph decode, Triton MoE decode, flash attention with sinks, grouped-GEMM MoE prefill
10 days ago
requirements.txt
Safe
129 Bytes
Flint chat demo
10 days ago