» Tag
memory
60 postsCogni: MCP Memory for LLMs Without LLM in the Retrieval Path
Cogni enhances LLMs with connected memory, enabling efficient reasoning and retrieval without relying on LLMs during the process.
Testing Go 1.27's New Goroutine Leak Detector
Go 1.27 introduces a new pprof profile for detecting goroutine leaks, enhancing memory management for developers.
New Storage Technology Could Enable GPUs to Reach Terabyte Capacities
High-Bandwidth Flash (HBF) could boost GPU memory capacity to terabytes, enhancing AI systems. Discover the implications of this new technology.
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.comUnderstanding NPU TOPS and Memory Bandwidth for Local LLM Performance
NPU TOPS and memory bandwidth are critical factors affecting local LLM performance.
Use-after-free Bug Exposed in Redis Client Library
A memory corruption bug was found in a Redis client library. Learn about its cause and resolution.
Mastering Java Loops: Memory Pitfalls and Optimization Strategies
Explore how JVM processes loops at the bytecode level and optimization strategies.
Large-Scale TensorCircuit Contractions: Disabling XLA GPU Autotuning
Impact of disabling XLA GPU autotuning on memory savings and runtime for large TensorCircuit contractions.
My Agent's Memory File Wasn't Wrong, It Was Just Six Weeks Stale
My agent's memory file provided accurate but outdated information, emphasizing the need for synchronization in engineering systems.
Rust File Watcher Consumed 23.6 GB of RAM, Ignoring Our Rules
A Rust file watcher ignored ignore rules, consuming 23.6 GB of RAM. Switching to NoCache resolved the issue.
C-to-Rust Fallacy: Automatic Refactoring Does Not Ensure Memory Security
Rust offers a compelling alternative to C/C++ with strong memory safety, but the effectiveness of automatic refactoring tools on security is questionable.