Liquid Inference launches aggregator routing across six inference providers
markjeffrey · x · 2026-10-08
Brett Harrison announces Liquid Inference, aggregating fast-growing token producers including Engy, Pearl Research Labs, AkashML, Hyperbolic, Boundless, and Zro. Mark Jeffrey compares it to a 'OneInch' or cheap router for LLM inference — a unified entry point routing requests across providers for lower cost.
More from Infra
- National Compute gifts $100M in compute credits to White House Genesis Mission — typewriters · 2026-10-08
- Ask: Is Qwen 3.8 Flash-Next Worth It Over 3.6 35B-A3B on 64GB RAM + 16GB VRAM? — msalsas · 2026-10-08
- vLLM cuts TTFT nearly 70% at ~100K throughput with DeepSeek NVFP4 kernels and fused ops — vllm_project · 2026-10-08
- Jensen Huang joins Satya Nadella at Surface event for RTX Spark-powered Surface Laptop Ultra — nvidia · 2026-10-08
- DeepSeek-V4.1-Flash on vLLM: 5.3x agentic throughput three weeks after day 0 — vllm_project · 2026-10-08
- Chrome silently ships a 425KB neural echo cancellation model; reverse-engineer finds 5.4dB gain — chadwallacehart · 2026-10-08