Skip to content
OBLAIDISH NEWS
signal_tag · 2_broadcasts

#llm-inference

// 2 transmissions tagged with #llm-inference

DeepSeek open-sources inference optimizations, 60–85% faster generation
TX_561684· AI

DeepSeek open-sources inference optimizations, 60–85% faster generation

DeepSeek released a paper detailing open‑source inference optimizations that deliver 60–85% faster text generation, giving engineers concrete techniques to speed up LLM deployments.

MedGemma model shows hardware-dependent nondeterminism
TX_912891· AI

MedGemma model shows hardware-dependent nondeterminism

A 4-bit MedGemma model produced different triage levels for the same patient case on a CPU and a GPU, revealing hardware-dependent nondeterminism in on-device medical triage [Dev.to] [Thinking Machines].