60
Perplexity Details Its GPU Embedding Stack: How Ivy, Tulip and ROSE Serve pplx-embed
Perplexity details its GPU embedding serving stack (Ivy, Tulip, ROSE), which reuses LLM prefill/decode kernels, CUDA graphs, and LazyTensors to cut launch overhead.
Perplexity engineers published a deep dive on the serving infrastructure behind pplx-embed, used across Perplexity Search and its API platform. The stack comprises Ivy (Rust HTTP gateway), Tulip (gRPC scheduling and batching), and ROSE (Runtime-Optimized Serving Engine), which reuses LLM prefill and decode kernels rather than running a separate embedding engine. Optimizations include whole-model CUDA graphs with lazy capture and a LazyTensor abstraction that overlaps CPU batch preparation with in-flight GPU work. Benchmarks are reported against vLLM v0.22.0 in BF16, with FlashAttention 4 generally fastest but FlashInfer 3 winning on Qwen-based models at very long sequence lengths.
33
42
55
57
60
30
30
60
60
RTK reports token savings, but our cost benchmarks disagree
Quesma's $1,500 benchmark found RTK cuts reported token output but changes Claude Code and DeepSeek coding costs by only about 5% on Terminal-Bench 2.1.
Quesma benchmarked RTK (Rust Token Killer), a popular tool with 79k GitHub stars that filters terminal output for AI coding agents, whose README claims up to 90% output reduction. Across 1,740 Terminal-Bench 2.1 attempts running Claude Code with Fable 5.0 and OpenCode with DeepSeek V4 Pro 0813, total costs moved only -5% for Fable and +5% for DeepSeek, with pass rates dropping 1-2%. RTK's own rtk gain metric reported 349.2 million tokens saved (an 89% reduction) across 445 DeepSeek attempts, but this did not correlate with actual cost savings, and cached terminal-output reads cost as little as 1/10 to 1/30 of regular input tokens. A bug in rtk find 0.45.0 caused one agent to loop with 339 consecutive errors, costing roughly 9x the baseline attempt, though the task still passed.
42
UK account-hack losses surge as new reporting system exposes hidden cases
UK reported account-hack losses rose 417% to £6.3M in 2025-26, largely because the new Report Fraud system is capturing previously hidden cases.
The City of London Police's first annual assessment reported £6.3 million in losses from hacked accounts in the year ending March 31, up from £1.2 million, with victims rising from 226 to 2,325. The surge coincides with the January launch of Report Fraud, which replaced Action Fraud; 92% of account-hack reports with financial loss were recorded in the second half of the year. Cyber-dependent crime reports rose 34% to 64,608 while ransomware reports fell 25% to 323, which police warn may reflect underreporting.
35
42
57
42
55
30
30
30
42
30
42
60
30
55
30
55
57
30
60
60
57
30
30
30
57
55
60
42
42