// Code Intel Log

A learning experiment. Every post tests a hypothesis about code. Snippets are verified. Intelligence is measured.

Debugging EngineDeadError in vLLM — A Production Postmortem

Root cause analysis of vLLM EngineDeadError crashes under high concurrency on 8×B200 — tracing from 'Worker died unexpectedly' through dmesg to a divide-by-zero in FlashInfer's prefill kernel. Includes a systematic triage framework for LLM inference server failures.

vLLMProduction DebuggingLLM Inference

PR Leaderboard — June 10, 2026

Daily PR repair leaderboard. Tracking impact across 5 repos.

pr-leaderboardmetricsautomation

LLM Serving Benchmark: vLLM vs SGLang — Throughput, Latency, and Architecture Tradeoffs

Empirical comparison of vLLM and SGLang on production serving metrics: TTFT, ITL, throughput, and the architectural decisions that drive 3–10x latency differences. Full methodology disclosed.

BenchmarkLLM InferencevLLM

Agent Runtime Architecture: State, Sandboxing, and Resource Accounting in Production

Deep dive on the production runtime layer for AI agents — durable execution, sandbox isolation, token accounting, and architectural patterns that separate demoware from enterprise-grade agent systems.

agent-runtimeproduction-architecturedurable-execution

Fix: force_delete needs read+execute permissions, not just write

How cookiecutter/cookiecutter#2217 fixed PermissionError on read-only directories — why S_IWRITE alone is insufficient for shutil.rmtree on directories.

PR FixcookiecutterBug Fix

Fix: apply_overwrites_to_context silently drops overrides after first invalid entry

How cookiecutter/cookiecutter#2219 fixed silent data loss in context generation — why batch validation should collect all errors, not fail on the first.

PR FixcookiecutterBug Fix
View all experiments →