Nexus Labs' fine-tuning and evaluation team lead demonstrated that a single evaluation metric like 84.2% accuracy on a 500-example set carries significant uncertainty, with a 95% bootstrap confidence …
Nexus Labs enabled speculative decoding in vLLM for a fine-tuned 8B model, achieving a 1.9x throughput gain, but discovered that greedy decoding with a draft model is not bit-identical to greedy decod…
Nexus Labs replaced 60% of its 11,247-line Python middleware for per-tenant LLM cost attribution, rate limiting, and provider failover with Bifrost's virtual keys and governance features. The migratio…
Nexus Labs reduced time-to-first-token (TTFT) from 480ms to 110ms on one tenant by enabling vLLM's prefix cache for agent workloads, while another tenant saw no improvement. The discrepancy was caused…
A 30-day production test at Nexus Labs compared three AI gateways—Bifrost, LiteLLM, and Portkey—measuring failover latency and overhead. Bifrost added 11ms p99 overhead with automatic provider fallbac…