» Tag
optimization
58 postsWhy reformatting prompts beats quantization for CPU LLM inference
Measured on a free ARM CPU box: rewriting prompts as label:value fact sheets cut LLM prefill time 6.5x while quantization tricks hurt accuracy.
Julia Introduces UnifiedIR to Merge Parser, Lowering and Optimizer IRs
Julia's compiler team unifies parsing, lowering and optimization under one IR, UnifiedIR, with a shared kind registry and source provenance tracking.
Colibri lets 744B-parameter GLM-5.2 run on just 25GB of RAM
Colibri is a single-file C engine that runs GLM-5.2's 744B MoE model on 25GB RAM with no GPU, streaming experts from NVMe on demand.
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.comFable 5 vs GPT-5.6 Sol on an NP-Hard Problem: Does /goal Help?
Claude Fable 5 and GPT-5.6 Sol tackle an NP-hard fiber-network problem, testing whether the /goal persistence feature actually improves results.
FlowOptimizer: Learning to Optimize via Unfolded Flows
MIT and Boston University researchers unveil FlowOptimizer, a flow-based learning-to-optimize framework that outperforms classical and learned optimizers by orders of magnitude.
Flare: Verifying MILP Reformulations with LLM-Based Theorem Proving
FLARE combines an LLM agent with the Lean proof assistant to formally verify MILP reformulations, backed by a new 109-formulation benchmark.
Inside OpenAI's Agent Loop: How Harness, API, and Inference Cut Costs
OpenAI engineers detail how harness, API, and inference layer optimizations cut cost and latency in agentic systems like Codex and ChatGPT Work.
How a Browser Video Renderer's Frame Time Was Cut by 80%
How four hidden bottlenecks in a browser video renderer were found and fixed, cutting frame time 80% and exposing a subtle opacity bug.
6x faster batched binary search in Rust via branch prediction fixes
scikit-learn's binary search bucketization gets a 6x Rust speedup by eliminating CPU branch mispredictions via branchless code.
Optimizing Elasticsearch Performance with AI Agents
AI agents are used for optimizing Elasticsearch performance. The results and design choices in this process are discussed.