» Tag
performance
289 postsllama.cpp CPU Offload Optimizations
Explore CPU offload optimizations for llama.cpp: disable CUDA graphs and target FFN sub-layers.
MemExchange: Utility-Driven Distributed Memory Reallocation for Datacenters
MemExchange is an innovative system optimizing memory management in datacenters.
ExLlamaV3 v1.0.0 - Major Performance Upgrades
ExLlamaV3 v1.0.0 brings major performance upgrades and new features for engineers.
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.comScaling is a Design Issue, Not Just a Setting
Autoscaling doesn't resolve design flaws. Scalability must be addressed during the design phase.
Understanding MasterMemory: Managing Static Game Data in Unity
MasterMemory provides an effective solution for managing static game data quickly and safely in Unity.
Noisia: Harmful Workload Generator for PostgreSQL
Noisia generates harmful workloads for PostgreSQL, aiding engineers in performance testing and issue identification.
Best Practices for Dataverse Schema Design in Enterprise Teams
Discover best practices for Dataverse schema design. Key strategies to prevent performance issues.
Hardware-Friendly LLM Design: AI Model Co-Design
How to balance accuracy, throughput, and interactivity in AI model design? Key insights into hardware-friendly LLM design.
ts-rust: An Experimental Rust Port of the TypeScript 7 Compiler
ts-rust is an experimental Rust port of the TypeScript 7 compiler, offering a fast and effective type checker.
I Developed an Efficient Maven Scheduler for Maximum Parallel Module Builds
My custom Maven scheduler enhances module build efficiency by allowing parallel execution, improving performance significantly.