Article
Security incident disclosure — July 2026
system
• • 93
Régis Pierrard
regisss
AI & ML interests
None yet
Recent Activity
upvoted an article 1 day ago
Security incident disclosure — July 2026 liked a Space 1 day ago
smolagents/hf-realtime-voice upvoted a changelog 1 day ago
Fine-Grained Token PresetsOrganizations
upvoted an article 1 day ago
liked a
Space 1 day ago
upvoted a changelog 1 day ago
Hugging Face Changelog
Fine-Grained Token Presets
• 44
upvoted an article 24 days ago
Article
GLM-5.2: Built for Long-Horizon Tasks
zai-org
• • 131 upvoted 3
articles about 1 month ago
Article
Intel XPU Kernel Skill: LLM-driven Triton kernel optimization for the Hugging Face Kernel Hub
danf
• • 11 Article
On the Shifting Global Compute Landscape
huggingface
• • 62 Article
Designing the hf CLI as an agent-optimized way to work with the Hub
celinah, Wauplin
• • 60 liked a
Space about 2 months ago
upvoted an article about 2 months ago
Article
Harness, Scaffold, and the AI Agent Terms Worth Getting Right
sergiopaniego, ariG23498
• • 132 upvoted 3
articles 3 months ago
Article
GGML and llama.cpp join HF to ensure the long-term progress of Local AI
- +4
ggerganov, ngxson, allozaur, lysandre, victor, julien-c
• • 508 Article
Welcome Gemma 4: Frontier multimodal intelligence on device
- +5
merve, pcuenq, sergiopaniego, burtenshaw, Steveeeeeeen, alvarobartt, SaylorTwift
• • 916 Article
Liberate your OpenClaw
- +6
clem, burtenshaw, pcuenq, jeffboudier, merve, nielsr, victor, mishig
• • 48 liked a
Space 4 months ago
upvoted 3
articles 4 months ago
Article
State of Open Source on Hugging Face: Spring 2026
huggingface
• • 94 Article
Introducing Modular Diffusers - Composable Building Blocks for Diffusion Pipelines
- +2
YiYiXu, OzzyGT, dn6, sayakpaul
• • 52 Article
Introducing Storage Buckets on the Hugging Face Hub
- +10
Wauplin, coyotte508, XciD, victor, julien-c, lhoestq, pierric, Sylvestre, hlarcher, rajatarya, seanses, assafvayner
• • 195 commented on Saying Thank You to a LLM Isn't Free — Measuring the Energy Cost of Politeness 4 months ago
KV caching enables to re-use what the model previously generated. That way, the model only focuses on the new tokens to generate.
Here is an illustrated explanation of KV caching: https://huggingface.co/blog/not-lain/kv-caching
upvoted an article 4 months ago
Article
KV Caching Explained: Optimizing Transformer Inference Efficiency
not-lain
• • 372 remove_develop
2
#57 opened 5 months ago
by 
FabienDanieau
add_back_main
2
#56 opened 5 months ago
by FabienDanieau