» Tag
performance
44 postsCo-Designing AI Model Attention for Fast, Interactive Long-Context Inference
Explore practical guidelines for optimizing AI model attention and inference efficiency.
Porting vLLM's Serving Stack to C++20: A 66 MiB Binary Without Python
The C++20 port of vLLM results in a 66 MiB binary without Python dependencies, achieving comparable speeds at high concurrency.
Sovereign Tech Fellowship for Rust Maintenance: June-July 2026 Report
Summary of Rust development and optimizations made during June-July 2026.
CommitBrief — AI code reviews, right in your terminal
A provider-agnostic, local-first CLI that reviews your staged changes, a historic range, or a whole GitHub pull request. Zero telemetry, no server. Free and open source.
commitbrief.comBursty Arrivals Accelerate LLM Inference Times
Bursty workloads have been found to unexpectedly speed up LLM inference.
Enhancing Postgres Performance with Row-Level Security
Tips for resolving performance issues in Postgres using Row-Level Security (RLS).
Apache Flink Accelerator Built with Rust
StreamFusion accelerates Apache Flink SQL using Rust, achieving 1.2-3 times the throughput of stock Flink. This boosts performance and efficiency.
DeepSeek-V4-Flash 0731: Full Precision Lossless Performance Test
DeepSeek-V4-Flash-0731 can be run at full precision with 176 GB memory. The project focuses on efficiency and performance testing.
Performance Boost in GreptimeDB: 10x Speedup with Rust PR
GreptimeDB achieves performance boost for Prometheus protocol with Rust PR.
Microsoft Introduces New AI Tools to Enhance Windows 11 Performance
Microsoft has launched new AI tools for Windows 11 performance analysis. The ETW MCP system aims to accelerate the identification of performance issues.
Processes That Threaten Your Database: Understanding Postgres Limits
How do processes running on Postgres servers affect the database? Insights on resource management with ClickHouse Managed Postgres.