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 collection 2 days ago
vLLM updated a model 2 days ago
hmellor/tiny-random-DeepseekV2ForCausalLM published a model 2 days ago
hmellor/tiny-random-DeepseekV2ForCausalLMOrganizations
published an article 9 days ago
published an article 27 days 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
• • 71