streaming 6
- Go Context Cancellation for LLM Streaming and Agent Calls: One Pattern That Cut Waste 47x
- Go pprof vs SLO Burn Rate: Finding the p99 Leak Before the Pager Fires
- Time-to-First-Token for Streamed LLM Responses: .NET 9 vs Node 22, Measured
- .NET 9 vs Node 22 as an LLM API Gateway: Requests per Second, p99 Latency and Memory, Measured
- gRPC Server-Streaming vs REST Long-Polling Under Load: p50, p99, Connections and CPU on .NET 8
- Streaming Azure OpenAI Responses in .NET: First Token in Under a Second