v5: Minimal lazy-loading architecture for instant startup ee3c612 MiniMax Agent commited on 30 days ago
Update Dockerfile to use app_v4 with background model loading 7ae4b71 MiniMax Agent commited on 30 days ago
Add v4 with background model loading - prevents timeout by loading model after server starts 44ffe48 MiniMax Agent commited on 30 days ago
Add complete local Ollama setup with OpenELM - includes setup script, API server, test scripts, and documentation 41831f1 MiniMax Agent commited on 30 days ago
Fix tokenizer issues: add sentencepiece dependency and robust loading strategy d36a46f MiniMax Agent commited on 30 days ago
Implement lazy loading - model loads on first request to avoid startup timeouts 2aeb5c7 MiniMax Agent commited on 30 days ago
Fix OpenELM tokenizer loading - use LlamaTokenizer as fallback 3daef91 MiniMax Agent commited on 30 days ago
Add Anthropic API compatible wrapper for OpenELM models 9604400 MiniMax Agent commited on 30 days ago