{"adoption": {"forks": 260, "observed_at": "2026-08-28T04:05:45.502950+00:00", "stars": 1863}, "canonical_url": "https://ross.abutalabs.com/products/ai-performance-engineering", "card": {"archived": false, "artifact_type": "learning-resource", "description": "Code, labs, and resources for O'Reilly AI Systems Performance Engineering: GPU optimization, distributed training, inference scaling, and full-stack tuning.", "domain": ["gpu-computing", "machine-learning", "deep-learning", "large-language-models", "performance", "developer-tools", "tutorials"], "enriched": true, "function": ["benchmarking", "gpu-computing", "llm-inference", "llm-training", "machine-learning", "deep-learning"], "health_score": 79, "homepage": null, "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["cfregly/ai-performance-engineering"], "name": "cfregly/ai-performance-engineering", "platform": ["python", "cross-platform"], "pushed_at": "2026-08-21T21:24:33+00:00", "repo": "cfregly/ai-performance-engineering", "stars": 1863, "tags": ["gpu-optimization", "distributed-training", "inference-serving", "profiling", "cuda", "pytorch", "triton", "vllm", "tensorrt-llm", "oreilly-book", "labs", "gpu", "linux"], "topics": [], "urls": [], "use_cases": ["learn how to profile and optimize GPU workloads with Nsight and PyTorch profilers", "understand distributed training parallelism strategies like FSDP, TP, PP, and MoE", "optimize high-throughput LLM inference with vLLM, SGLang, and TensorRT-LLM", "write custom GPU kernels with Triton and the PyTorch compiler stack", "reduce cost per token when serving large models", "hands-on labs for AI systems performance tuning"], "what_it_is": "Code, labs, and resources accompanying the O'Reilly book 'AI Systems Performance Engineering', covering GPU optimization, distributed training, and inference scaling. It includes thousands of lines of PyTorch and CUDA C++ examples plus profiling case studies for modern NVIDIA GPUs.", "when_to_avoid": ["you need a production-ready tool or framework rather than educational material", "you work exclusively on non-NVIDIA hardware", "you are a beginner looking for basic ML tutorials rather than performance engineering"], "when_to_choose": ["you are an ML or systems engineer building or operating training/inference at scale", "you want empirical, profiling-driven GPU optimization techniques", "you need to learn disaggregated prefill/decode serving and KV-cache management", "you want a structured book plus runnable code examples"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/ai-performance-engineering", "repo": "cfregly/ai-performance-engineering", "role": "main", "score": 63}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:05:45.502950+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T03:15:38.536484+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b11685b5a2a55d1049e1e74d732563820e67cb8cd9d7a7dc791da4db27108715", "fetched_at": "2026-08-28T04:05:45.502950+00:00", "kind": "readme", "missing": false, "url": "https://github.com/cfregly/ai-performance-engineering"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:05:45.502950+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T03:15:38.536484+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b11685b5a2a55d1049e1e74d732563820e67cb8cd9d7a7dc791da4db27108715", "fetched_at": "2026-08-28T04:05:45.502950+00:00", "kind": "readme", "missing": false, "url": "https://github.com/cfregly/ai-performance-engineering"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T03:15:38.536484+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b11685b5a2a55d1049e1e74d732563820e67cb8cd9d7a7dc791da4db27108715", "fetched_at": "2026-08-28T04:05:45.502950+00:00", "kind": "readme", "missing": false, "url": "https://github.com/cfregly/ai-performance-engineering"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:05:45.502950+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:05:45.502950+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:05:45.502950+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T03:15:38.536484+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b11685b5a2a55d1049e1e74d732563820e67cb8cd9d7a7dc791da4db27108715", "fetched_at": "2026-08-28T04:05:45.502950+00:00", "kind": "readme", "missing": false, "url": "https://github.com/cfregly/ai-performance-engineering"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:05:45.502950+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:05:45.502950+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T03:15:38.536484+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b11685b5a2a55d1049e1e74d732563820e67cb8cd9d7a7dc791da4db27108715", "fetched_at": "2026-08-28T04:05:45.502950+00:00", "kind": "readme", "missing": false, "url": "https://github.com/cfregly/ai-performance-engineering"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:05:45.502950+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:05:45.502950+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:05:45.502950+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T03:15:38.536484+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b11685b5a2a55d1049e1e74d732563820e67cb8cd9d7a7dc791da4db27108715", "fetched_at": "2026-08-28T04:05:45.502950+00:00", "kind": "readme", "missing": false, "url": "https://github.com/cfregly/ai-performance-engineering"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:05:45.502950+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:05:45.502950+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T03:15:38.536484+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b11685b5a2a55d1049e1e74d732563820e67cb8cd9d7a7dc791da4db27108715", "fetched_at": "2026-08-28T04:05:45.502950+00:00", "kind": "readme", "missing": false, "url": "https://github.com/cfregly/ai-performance-engineering"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T03:15:38.536484+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b11685b5a2a55d1049e1e74d732563820e67cb8cd9d7a7dc791da4db27108715", "fetched_at": "2026-08-28T04:05:45.502950+00:00", "kind": "readme", "missing": false, "url": "https://github.com/cfregly/ai-performance-engineering"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T03:15:38.536484+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b11685b5a2a55d1049e1e74d732563820e67cb8cd9d7a7dc791da4db27108715", "fetched_at": "2026-08-28T04:05:45.502950+00:00", "kind": "readme", "missing": false, "url": "https://github.com/cfregly/ai-performance-engineering"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T03:15:38.536484+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b11685b5a2a55d1049e1e74d732563820e67cb8cd9d7a7dc791da4db27108715", "fetched_at": "2026-08-28T04:05:45.502950+00:00", "kind": "readme", "missing": false, "url": "https://github.com/cfregly/ai-performance-engineering"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 98, "longevity": 35, "rhythm": 35}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["no_releases"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 499, "days_push": 12, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 63, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}