feat: add HF real workload datasets (10k), streaming benchmark results, and BYOK budget tests 7191aa9 Ypeng12 commited on 5 days ago
feat: implement server-side FrugalGPT cascade router, prompt adaptation, and offline Pareto sweeps 26d7b76 Ypeng12 commited on 25 days ago
Fix SQLite, OpenAI mock, circuit breaker fallback for pinned models, cache isolation, prefix cache answers, docs relative paths, and integration tests 0a1d5dd Ypeng12 commited on 27 days ago
feat: implement streaming request dedup, cache-affinity trie routing, speculative cascade, vegas concurrency limiter, web UI playground, and multi-tenant wallet billing 80db329 Ypeng12 commited on 29 days ago
fix: resolve circuit breaker mocking and update router test assertions d142175 Ypeng12 commited on Jun 19