{"title":"llm-d 1.0’s passing TPU badges do not validate every documented TPU path","description":"The sampled records distinguish release-validation lanes, checked passing badges and documented configurations, but do not establish exact v1.0.0 runtime validation for every path—or validation of routing, offload and disaggregation together.","dataset_id":"spd:llm-d-1-0-which-tpu-and-gpu-serving-paths-have-published-test-evidence-95e8db12","canonical_url":"https://superpowerdaily.com/research/llm-d-1-0-which-tpu-and-gpu-serving-paths-have-published-test-evidence-95e8db12","version_url":"https://superpowerdaily.com/research/llm-d-1-0-which-tpu-and-gpu-serving-paths-have-published-test-evidence-95e8db12","version":"Live","snapshot_hash":null,"date_created":null,"date_modified":"2026-10-22T02:38:16.914Z","license":{"name":"Superpower Daily data reuse terms","url":"https://superpowerdaily.com/terms"},"license_url":"https://superpowerdaily.com/terms","coverage_note":"This is a bounded audit of three guides, not every llm-d deployment or feature cross-product. It excludes CPU/NPU configurations, baseline-only serving, wide expert parallelism and multimodal guides. Passing statuses were checked only for the supplied GKE GPU/TPU badges. The saved Google announcement snapshot carries a retrieval time of October 21 at 20:31:58.905 UTC, later than the stated cutoff; it is not treated as pre-cutoff test verification.","measurement_technique":["Reassess the supplied saved evidence only. Preserve the original October 21, 2026, 20:30 UTC evidence cutoff and collection record of October 21, 2026, 20:30:57.479 UTC; this synthesis is not a new collection, experiment or calculation.","Bound the sample to TPU/GPU configurations in the v1.0.0-tagged precise prefix-cache routing, tiered prefix-cache and prefill/decode disaggregation guides, together with their release-matrix entries.","Use the supplied Google and IBM announcements as attributed launch context, and project/router release notes as version context—not as independent deployment validation.","Plan an evidence matrix with accelerator and generation, inference engine, serving technique, connector or backend, guide version, release lane, checked result and provenance limits. Keep release-lane existence separate from a checked passing result.","Classify evidence as checked passing release-branch status, published lane with outcome not checked, explicit manual-validation statement, documented without a corresponding sampled release lane, or indeterminate exact-version/combined-feature validation. Do not calculate a tested-share percentage from the supplied grouped records."],"methodology":["Reassess the supplied saved evidence only. Preserve the original October 21, 2026, 20:30 UTC evidence cutoff and collection record of October 21, 2026, 20:30:57.479 UTC; this synthesis is not a new collection, experiment or calculation.","Bound the sample to TPU/GPU configurations in the v1.0.0-tagged precise prefix-cache routing, tiered prefix-cache and prefill/decode disaggregation guides, together with their release-matrix entries.","Use the supplied Google and IBM announcements as attributed launch context, and project/router release notes as version context—not as independent deployment validation.","Plan an evidence matrix with accelerator and generation, inference engine, serving technique, connector or backend, guide version, release lane, checked result and provenance limits. Keep release-lane existence separate from a checked passing result.","Classify evidence as checked passing release-branch status, published lane with outcome not checked, explicit manual-validation statement, documented without a corresponding sampled release lane, or indeterminate exact-version/combined-feature validation. Do not calculate a tested-share percentage from the supplied grouped records."],"metrics":[{"label":"Verified observations","value":"0","detail":"0 measured fields"},{"label":"Supported claims","value":"9","detail":"9 material findings"},{"label":"Cited sources","value":"8","detail":"8 primary or authoritative"},{"label":"Research score","value":"80","detail":"Automated topic and evidence score"}],"columns":[{"key":"entity","label":"Entity"},{"key":"metric","label":"Metric"},{"key":"value","label":"Value"},{"key":"unit","label":"Unit"},{"key":"observed","label":"Observed"},{"key":"source","label":"Source"},{"key":"transform","label":"Transform"}],"data":[],"sources":[{"name":"Google Cloud","title":"llm-d 1.0, an open source stack for distributed inference | Google Cloud Blog","url":"https://cloud.google.com/blog/topics/ai-infrastructure/llm-d-1-0-an-open-source-stack-for-distributed-inference","records":0},{"name":"IBM Research","title":"llm-d 1.0 hardens open-source AI inference for production","url":"https://research.ibm.com/blog/llmd-1-0-is-ready-for-production-inference-serving","records":0},{"name":"llm-d","title":"raw.githubusercontent.com","url":"https://raw.githubusercontent.com/llm-d/llm-d/v1.0.0/guides/pd-disaggregation/README.md","records":0},{"name":"llm-d","title":"raw.githubusercontent.com","url":"https://raw.githubusercontent.com/llm-d/llm-d/v1.0.0/guides/precise-prefix-cache-routing/README.md","records":0},{"name":"llm-d","title":"raw.githubusercontent.com","url":"https://raw.githubusercontent.com/llm-d/llm-d/v1.0.0/guides/tiered-prefix-cache/README.md","records":0},{"name":"llm-d","title":"raw.githubusercontent.com","url":"https://raw.githubusercontent.com/llm-d/llm-d/v1.0.0/release/README.md","records":0},{"name":"llm-d","title":"Releases · llm-d/llm-d","url":"https://github.com/llm-d/llm-d/releases","records":0},{"name":"llm-d","title":"Releases · llm-d/llm-d-router","url":"https://github.com/llm-d/llm-d-router/releases","records":0}],"provenance":{"publisher":"Superpower Daily","source_count":8,"source_urls":["https://cloud.google.com/blog/topics/ai-infrastructure/llm-d-1-0-an-open-source-stack-for-distributed-inference","https://research.ibm.com/blog/llmd-1-0-is-ready-for-production-inference-serving","https://raw.githubusercontent.com/llm-d/llm-d/v1.0.0/guides/pd-disaggregation/README.md","https://raw.githubusercontent.com/llm-d/llm-d/v1.0.0/guides/precise-prefix-cache-routing/README.md","https://raw.githubusercontent.com/llm-d/llm-d/v1.0.0/guides/tiered-prefix-cache/README.md","https://raw.githubusercontent.com/llm-d/llm-d/v1.0.0/release/README.md","https://github.com/llm-d/llm-d/releases","https://github.com/llm-d/llm-d-router/releases"],"methodology":["Reassess the supplied saved evidence only. Preserve the original October 21, 2026, 20:30 UTC evidence cutoff and collection record of October 21, 2026, 20:30:57.479 UTC; this synthesis is not a new collection, experiment or calculation.","Bound the sample to TPU/GPU configurations in the v1.0.0-tagged precise prefix-cache routing, tiered prefix-cache and prefill/decode disaggregation guides, together with their release-matrix entries.","Use the supplied Google and IBM announcements as attributed launch context, and project/router release notes as version context—not as independent deployment validation.","Plan an evidence matrix with accelerator and generation, inference engine, serving technique, connector or backend, guide version, release lane, checked result and provenance limits. Keep release-lane existence separate from a checked passing result.","Classify evidence as checked passing release-branch status, published lane with outcome not checked, explicit manual-validation statement, documented without a corresponding sampled release lane, or indeterminate exact-version/combined-feature validation. Do not calculate a tested-share percentage from the supplied grouped records."],"snapshot_hash":null},"distributions":{"csv":"https://superpowerdaily.com/api/research/llm-d-1-0-which-tpu-and-gpu-serving-paths-have-published-test-evidence-95e8db12?format=csv","json":"https://superpowerdaily.com/api/research/llm-d-1-0-which-tpu-and-gpu-serving-paths-have-published-test-evidence-95e8db12?format=json"}}