How a Transformers Model Loads in vLLM
🧠
4
Animated walkthrough of vLLM's Transformers modeling backend
Harry Mellor
hmellor
AI & ML interests
Machine Learning Engineer @ HF
Recent Activity
updated a Space 2 days ago
hmellor/transformers-modeling-backend-for-vllm upvoted an article 4 days ago
Transformers now runs llama.cpp quants new activity 9 days ago
deepseek-ai/dspark_gemma4_12b_block7:Remove stray top-level rope parametersOrganizations
updated a
Space 2 days ago
upvoted an article 4 days ago
Article
Transformers now runs llama.cpp quants
- +1
marcsun13, ArthurZ, lysandre
• • 68 Remove stray top-level rope parameters
#3 opened 9 days ago
by hmellor
liked a
Space 15 days ago
Make compatible with Transformers 5.17
#12 opened 15 days ago
by hmellor
updated a
collection about 2 months ago
updated a
model about 2 months ago
published a
model about 2 months ago
published an article about 2 months ago
Article
The Transformers modeling backend serves DeepSeek-R1 at native speed
hmellor
• • 2 upvoted an article about 2 months ago
Article
Anatomy of a Frontier Lab Agent Intrusion: A Technical Timeline of the July 2026 Incident
- +2
hlarcher, XciD, raphael-gl, chris-rannou
• • 506 upvoted a changelog 2 months ago
Hugging Face Changelog
Egress metrics for users and organizations
• 136
upvoted an article 2 months ago
Article
The Transformers modeling backend is now as fast as native vLLM
hmellor
• • 1 published an article 2 months ago
Article
The Transformers modeling backend is now as fast as native vLLM
hmellor
• • 1 upvoted an article 2 months ago
Article
Security incident disclosure — July 2026
system
• • 798 upvoted an article 3 months ago
Article
Native-speed vLLM transformers modeling backend
hmellor, lysandre
• • 76 published a
Space 3 months ago
published an article 3 months ago
Article
Native-speed vLLM transformers modeling backend
hmellor, lysandre
• • 76 updated a
dataset 3 months ago
updated 2
Spaces 4 months ago