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
HelloSun
/
fint-epqv2
Like
2
llama.cpp
flint
Mixture of Experts
expert-offloading
cpu-inference
License:
mit
Model card
Files
Files and versions
xet
Community
Copy to bucket
c255fee
fint-epqv2
/
src
732 kB
Ctrl+K
Ctrl+K
1 contributor
History:
5 commits
HelloSun
Hot/cold expert analysis: skew, profile pinning hit rates; fix hit counting and default pin fraction
55dfdd3
verified
24 days ago
CMakeLists.txt
Safe
2.26 kB
Add Flint expert paging port and memory benchmark
24 days ago
llama-context.cpp
Safe
170 kB
Add Flint expert paging port and memory benchmark
24 days ago
llama-graph.cpp
Safe
159 kB
Add Flint expert paging port and memory benchmark
24 days ago
llama-model.cpp
Safe
188 kB
Add Flint expert paging port and memory benchmark
24 days ago
llama.cpp
Safe
23.1 kB
Add Flint expert paging port and memory benchmark
24 days ago
sdq_buft.cpp
Safe
9 kB
Add Flint expert paging port and memory benchmark
24 days ago
sdq_moe.cpp
Safe
55.3 kB
Upload v2 memory tiers (default and forced row-parallel) with path counters
24 days ago
sdq_pager.cpp
Safe
103 kB
Hot/cold expert analysis: skew, profile pinning hit rates; fix hit counting and default pin fraction
24 days ago
sdq_pager.h
Safe
23.6 kB
Upload v2 memory tiers (default and forced row-parallel) with path counters
24 days ago