Edge-cloud multi-agent with decentralization
Edge-cloud multi-agent architecture with decentralized management: how to reduce latency, traffic, and enhance resilience in mobile automation. –>
Low Latency Systems and Communication Control
English:
How to design low-latency systems: controlling communication, Disruptor, Aeron, and the trade-offs between speed and architecture.
CPU-free LLM inference without CPU involvement
CPU-free LLM inference: how to remove the CPU from the critical path and stabilize latency in LLM serving architectures.
Agentic systems without context overload
How an agentic system manages the context window through Journal, Review, and Timeline, reducing latency and improving consistency in multi-agent reasoning.
KV cache optimization for multi-LoRA agents
KV cache optimization in multi-LoRA serving: how ForkKV reduces memory consumption and increases throughput of LLM inference.
Root cause analysis as code in SRE systems
Root cause analysis (RCA) hinges on scale and the human factor. Meta’s approach with DrP demonstrates how to turn debugging into a reproducible engineering process. The problem does not manifest immediately — until the system reaches organizational scale. Incidents begin to recur, but each time they are investigated anew. Knowledge of where to look for … Read more
Platform Program split at Uber under growth pressure
Platform Program split became a key step for Uber when the growth of the team began to hinder development. This decision changed both the architecture and the organization simultaneously. The problem manifested not at the code level, but at the level of team interaction. When Uber’s engineering organization grew to about 100 people, the division … Read more
P2P Model Distribution in Kubernetes Without Bottlenecks
P2P model distribution in Kubernetes with Dragonfly: how to reduce traffic to the origin and accelerate the delivery of large models from Hugging Face and ModelScope.
Kubernetes Gateway API instead of Ingress NGINX
Migration from Ingress NGINX is becoming mandatory: EOL and vulnerabilities make the transition to Kubernetes Gateway API a matter of resilience and security. The problem does not manifest immediately — until control over incoming traffic becomes a point of systemic risk. Ingress NGINX has long been the de facto standard for Kubernetes, but its lifecycle … Read more
Symbolic execution for BPF malware analysis
Symbolic execution simplifies the analysis of BPF malware and eliminates a bottleneck in reverse engineering. This approach allows for the automatic reconstruction of “magic” packets to trigger backdoors. The problem does not manifest immediately — until the analysis of BPF malware encounters the complexity of the filters themselves. The classic Berkeley Packet Filter operates as … Read more