Article
Three of ten optimisations did nothing: video generation on one card
ecohash
• 
EcoHash Dev Team
ecohash
AI & ML interests
Open-model inference APIs, OpenAI-compatible endpoints, LLM · vision · speech · video, RTX PRO 6000 GPU Cloud
Recent Activity
published an article 1 day ago
Three of ten optimisations did nothing: video generation on one card updated a Space 3 days ago
ecohash-ai/README published an article 10 days ago
One vLLM flag doubled the concurrency a single card holdsOrganizations
published an article 1 day ago
published an article 10 days ago
Article
One vLLM flag doubled the concurrency a single card holds
ecohash-ai
• published an article 11 days ago
Article
A voice agent in three API calls
ecohash-ai
• published an article 11 days ago
Article
Picking an open model per task, with the numbers attached
ecohash-ai
• published an article 11 days ago
Article
What 96 GB on one card actually buys you
ecohash-ai
•