Liquid Inference ships DeepSeek V4.1-Flash support, ComfyUI plugin over weekend
AccBalanced · x · 2026-10-19
Brett Harrison announces a weekend batch of Liquid Inference integrations: DeepSeek V4.1-Flash-1017 model support with DeepSeek Harness, an Openclaw plugin for agent backend, a ComfyUI plugin for image/video generation and editing, plus embedding models. "We ship every day."
More from Infra
- Data centers use just 0.85% of global primary energy, by the numbers — DarinFeinstein · 2026-10-19
- vLLM 0.32.0 adds structured-decision API reading first-token probabilities — AccBalanced · 2026-10-19
- GPU pricing is now set by cost of capital, not spot rates, argues Maya — AccBalanced · 2026-10-19
- Analyst revises 2027 datacenter forecast up to +50GW, citing satellite imagery — AccBalanced · 2026-10-19
- MCP tool's responses were 62% wasted tokens — here's the fix that cut them by 3x — S_B_B_B_K · 2026-10-19
- Cisco and NVIDIA unveil USFP optical module plan: 4x bandwidth density — shashib · 2026-10-19