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
HelloSun
/
laguna-s-2.1-Q4_K_M_EPQ
Like
0
Text Generation
GGUF
Mixture of Experts
expert-paging
epq
q4_k_m
laguna
cpu-inference
conversational
arxiv:
2602.03921
Model card
Files
Files and versions
xet
Community
Copy to bucket
new
main
laguna-s-2.1-Q4_K_M_EPQ
6.43 MB
Ctrl+K
Ctrl+K
1 contributor
History:
7 commits
HelloSun
Add Least-Stale eviction experiment (LRU vs stale/current queues)
5a0e9c2
verified
2 days ago
results
Add Least-Stale eviction experiment (LRU vs stale/current queues)
2 days ago
.gitattributes
Safe
1.52 kB
initial commit
3 days ago
0001-epq-laguna.patch
Safe
5.35 kB
EPQ expert-paging port for Laguna-S-2.1 Q4_K_M (source + results)
3 days ago
FILES.md
Safe
3.15 kB
Add Least-Stale eviction experiment (LRU vs stale/current queues)
2 days ago
README.md
Safe
16.9 kB
Add Least-Stale eviction experiment (LRU vs stale/current queues)
2 days ago
build.sh
Safe
1.57 kB
EPQ expert-paging port for Laguna-S-2.1 Q4_K_M (source + results)
3 days ago
make_strict_table.py
Safe
2.81 kB
Add 64 GiB strict RAM-limit experiment
3 days ago
sdq_buft.cpp
Safe
8.82 kB
EPQ expert-paging port for Laguna-S-2.1 Q4_K_M (source + results)
3 days ago
sdq_cli.cpp
Safe
40.5 kB
Add top-k ablation: original 10 vs 4 (speed, SSD, PPL)
3 days ago
sdq_moe.cpp
Safe
34.9 kB
EPQ expert-paging port for Laguna-S-2.1 Q4_K_M (source + results)
3 days ago
sdq_pager.cpp
Safe
104 kB
Add Least-Stale eviction experiment (LRU vs stale/current queues)
2 days ago
sdq_pager.h
Safe
22.8 kB
Add Least-Stale eviction experiment (LRU vs stale/current queues)
2 days ago
strict_bench.py
Safe
6.84 kB
EPQ expert-paging port for Laguna-S-2.1 Q4_K_M (source + results)
3 days ago
topk_ablation.py
Safe
8.23 kB
Add Least-Stale eviction experiment (LRU vs stale/current queues)
2 days ago
verify_moe_layer_laguna.py
Safe
4.36 kB
EPQ expert-paging port for Laguna-S-2.1 Q4_K_M (source + results)
3 days ago