🤖 Perplexity Reuses LLM Stack for Efficient GPU Embedding

Perplexity's GPU embedding stack is a single engine with three services: an HTTP gateway that parses JSON, tokenises and splits large requests into...

#RAGEmbeddings #InferenceOptimization #HardwareChips #AI #AIPulse

🤖 Deepseek's 160,000-Chip Huawei Cluster to Reduce Nvidia Reliance

The plan is a cluster of 160,000 Ascend 950DT chips, deployed in Inner Mongolia for inference only, with training workloads still run on Nvidia. The memory...

#HardwareChips #ChineseAI #InferenceOptimization #AI #AIPulse

🤖 Perplexity's Qwen Engine Outperforms MLX on Apple Silicon

Perplexity's open sourced Lily inference engine, optimized for Qwen3.6 35B A3B on Apple silicon Macs, achieves better performance than the default MLX stack by...

#InferenceOptimization #OpenSource #HardwareChips #AI #AIPulse