Последние новости
⚑ Сообщить о проблемеTech news from the best sources
Building a Distributed GPU Cluster for LLM Inference on Idle Apple Silicon Macs
A single M2 Max Mac Studio can serve 8‑token‑per‑second Llama‑2‑7B inference, yet most developers leave that compute idle overnight. ## Inventory an…
Perseus: A Fail-Slow Detection Framework for Cloud Storage Systems (2023)
Abstract: The newly-emerging “fail-slow” failures plague both software and hardware where the victim components are still functioning yet with degra…
Kafka Partitions and Consumer Groups: How to Prevent Head-of-Line Blocking
Apache Kafka is celebrated for its incredible horizontal throughput, capable of streaming millions of messages per second. Yet, many engineering tea…
Treat Tool Intent as a Deduped Outbox Before Planner Retries Double-Commit
Last Tuesday I sat with a sequence dump that looked successful until I counted the tickets twice. The planner had asked for one incident record, and…
Treat Client Timeout as an In-Doubt Lease Before You Replay Shared Tool Calls
Last Tuesday I sat with a planner log that looked almost boring until I lined up two clocks. The client aborted a tool call at thirty seconds, then…
Squalk: an old-school forum engine built on Nostr (NIP-29 groups, NIP-7D threads)
I miss classic forums: slow, asynchronous threads that stay readable and searchable for years, instead of knowledge dissolving into chat scrollback.…
"The write was acknowledged" means less than you think
I spent years operating databases for payment platforms, where a lost write isn't a bug, it's a regulatory conversation. That environment teaches yo…
Tsampi BFT: Leaderless One-Round Voting with Parameterized Finality
Tsampi BFT is a leaderless Byzantine fault-tolerant state-replication protocol with one Vote round per Proposed Block and exact-lineage finality in…