Article
The Transformers modeling backend serves DeepSeek-R1 at native speed
hmellor
• • 2
Harry Mellor
hmellor
AI & ML interests
Machine Learning Engineer @ HF
Recent Activity
updated a Space 5 days ago
hmellor/transformers-modeling-backend-for-vllm updated a collection 7 days ago
vLLM updated a model 7 days ago
hmellor/tiny-random-DeepseekV2ForCausalLMOrganizations
published an article 14 days ago
published an article about 1 month ago
Article
The Transformers modeling backend is now as fast as native vLLM
hmellor
• • 1 published an article about 1 month ago
Article
Native-speed vLLM transformers modeling backend
hmellor, lysandre
• • 73