{"schema_version":"onlylabs.public_signal.v1","title":"Baseten Writing: Agentic Inference Optimization Faster Than Sota","description":"Baseten writing signal with public source context, captured evidence pages, related signals, and category-scoped analysis context.","url":"https://onlylabs.fyi/signals/62020fe3-536a-4733-9a1c-f750baf0026e","json_url":"https://onlylabs.fyi/signals/62020fe3-536a-4733-9a1c-f750baf0026e/signal.json","generated_at":"2026-10-12T17:41:52.139Z","evidence_latest_fetched_at":"2026-10-03T00:02:34.910318+00:00","signal_first_seen_at":"2026-10-03T00:00:54.440942+00:00","org":{"slug":"baseten","name":"Baseten","category":"neocloud","category_label":"Neocloud","dossier_url":"https://onlylabs.fyi/labs/baseten","dossier_json_url":"https://onlylabs.fyi/labs/baseten/dossier.json"},"related_urls":{"signal":"https://onlylabs.fyi/signals/62020fe3-536a-4733-9a1c-f750baf0026e","signal_json":"https://onlylabs.fyi/signals/62020fe3-536a-4733-9a1c-f750baf0026e/signal.json","source":"https://www.baseten.co/blog/agentic-inference-optimization-faster-than-sota/","lab_dossier":"https://onlylabs.fyi/labs/baseten","lab_dossier_json":"https://onlylabs.fyi/labs/baseten/dossier.json","analysis":"https://onlylabs.fyi/analysis/baseten","analysis_json":"https://onlylabs.fyi/analysis/baseten/analysis.json","analysis_evidence_json":"https://onlylabs.fyi/analysis/baseten/evidence.json","category":"https://onlylabs.fyi/neoclouds","category_json":"https://onlylabs.fyi/neoclouds.json","category_feed":"https://onlylabs.fyi/neoclouds/feed.xml","category_signals_json":"https://onlylabs.fyi/signals.json?category=neocloud","topic":"https://onlylabs.fyi/topics/talking","topic_signals_json":"https://onlylabs.fyi/topics/talking/signals.json?category=neocloud","topic_feed":"https://onlylabs.fyi/topics/talking/feed.xml?category=neocloud","data_business":null},"answer_pack":{"answer":"Baseten published Agentic Inference Optimization Faster Than Sota. This talking signal gives public context for research themes, product direction, policy, or launch framing. High-signal details: Technical post on inference optimization from established AI infra company · Agentic inference optimization: 50-90% faster engines Announcing our partnership with OpenAI . Read more Model performance Agentic inference optimization: 50-90% faster.... onlylabs links this event to 1 captured evidence page and 6 related writing signals.","signal_desk":"talking","source_context":{"source_url":"https://www.baseten.co/blog/agentic-inference-optimization-faster-than-sota/","source_host":"baseten.co","occurred_at":"2026-10-02T21:09:34+00:00","first_seen_at":"2026-10-03T00:00:54.440942+00:00","date_source":"sitemap.lastmod","context":null},"context_markers":[{"label":"Lab","value":"Baseten","source":"signal"},{"label":"Signal desk","value":"talking","source":"signal"},{"label":"Source host","value":"baseten.co","source":"source"},{"label":"Notability","value":"Technical post on inference optimization from established AI infra company","source":"signal"},{"label":"Watch term","value":"Eval methodology","source":"evidence"},{"label":"Watch term","value":"Model card","source":"model"},{"label":"Watch term","value":"Infrastructure","source":"evidence"},{"label":"Watch term","value":"Agents and tool use","source":"evidence"}],"evidence_coverage":{"target_pages":1,"captured_pages":1,"readable_pages":1,"capture_methods":["plain"],"missing_page_urls":[],"failed_page_urls":[],"blocked_page_urls":[],"page_urls":["https://www.baseten.co/blog/agentic-inference-optimization-faster-than-sota/"],"related_signals":6,"has_source_url":true,"latest_page_fetched_at":"2026-10-03T00:02:34.910318+00:00"},"data_business":{"matches":false,"lanes":[],"matched_terms":[],"score":null,"reason":null},"agent_handoff":{"signal_json":"https://onlylabs.fyi/signals/62020fe3-536a-4733-9a1c-f750baf0026e/signal.json","dossier_json":"https://onlylabs.fyi/labs/baseten/dossier.json","analysis_json":"https://onlylabs.fyi/analysis/baseten/analysis.json","analysis_evidence_json":"https://onlylabs.fyi/analysis/baseten/evidence.json","topic_signals_json":"https://onlylabs.fyi/topics/talking/signals.json?category=neocloud","topic_feed":"https://onlylabs.fyi/topics/talking/feed.xml?category=neocloud","category_signals_json":"https://onlylabs.fyi/signals.json?category=neocloud","data_radar_json":null,"opportunities_json":null},"analysis_playbook":{"objective":"Turn public writing and discussion into a readable map of research themes, product framing, policy posture, launch narratives, and market attention.","evidence_focus":["post title","source URL","captured page text","HN traction","linked model or paper references","publication date"],"extraction_questions":["Which themes are labs choosing to explain publicly?","Which posts are attracting outside discussion?","Which writing reframes a recent release, model, hiring wave, or policy stance?","Which posts mention data, evals, infrastructure, safety, or deployment workflows?"],"signal_questions":["What public theme, launch framing, or research direction does this writing signal expose?","Which themes are labs choosing to explain publicly?","Which posts are attracting outside discussion?","Do the 6 related writing signals show a repeated pattern?"],"output_fields":["org","theme","public_framing","traction","evidence_url"],"data_business_relevance":"Data-business lane extraction is scoped to frontier labs; for this category, keep conclusions tied to category-specific strategy, source evidence, and follow-up questions.","required_sources":[{"label":"signal_json","url":"https://onlylabs.fyi/signals/62020fe3-536a-4733-9a1c-f750baf0026e/signal.json","required":true},{"label":"source","url":"https://www.baseten.co/blog/agentic-inference-optimization-faster-than-sota/","required":true},{"label":"dossier_json","url":"https://onlylabs.fyi/labs/baseten/dossier.json","required":true},{"label":"analysis_evidence_json","url":"https://onlylabs.fyi/analysis/baseten/evidence.json","required":true},{"label":"topic_signals_json","url":"https://onlylabs.fyi/topics/talking/signals.json?category=neocloud","required":false},{"label":"data_radar_json","url":null,"required":false}],"expected_output":["one-paragraph source-grounded interpretation","category-specific implication","confidence and missing evidence","recommended next source to inspect"],"prompt_seed":"Using only the linked onlylabs JSON, captured source context, and cited evidence, analyze Baseten's writing signal \"Agentic Inference Optimization Faster Than Sota\" for neocloud strategy."},"semantic_triples":[{"subject":"Baseten","predicate":"published","object":"Agentic Inference Optimization Faster Than Sota","text":"Baseten published Agentic Inference Optimization Faster Than Sota."},{"subject":"Agentic Inference Optimization Faster Than Sota","predicate":"is classified as","object":"writing signal","text":"Agentic Inference Optimization Faster Than Sota is classified as writing signal."},{"subject":"Agentic Inference Optimization Faster Than Sota","predicate":"belongs to","object":"talking desk","text":"Agentic Inference Optimization Faster Than Sota belongs to talking desk."},{"subject":"Agentic Inference Optimization Faster Than Sota","predicate":"has evidence coverage","object":"1 captured evidence page","text":"Agentic Inference Optimization Faster Than Sota has evidence coverage 1 captured evidence page."},{"subject":"Agentic Inference Optimization Faster Than Sota","predicate":"has captured page count","object":"1","text":"Agentic Inference Optimization Faster Than Sota has captured page count 1."},{"subject":"Agentic Inference Optimization Faster Than Sota","predicate":"has readable page count","object":"1","text":"Agentic Inference Optimization Faster Than Sota has readable page count 1."},{"subject":"Agentic Inference Optimization Faster Than Sota","predicate":"has related signal count","object":"6","text":"Agentic Inference Optimization Faster Than Sota has related signal count 6."},{"subject":"Agentic Inference Optimization Faster Than Sota","predicate":"has analysis playbook objective","object":"Turn public writing and discussion into a readable map of research themes, product framing, policy posture, launch narratives, and market attention.","text":"Agentic Inference Optimization Faster Than Sota has analysis playbook objective Turn public writing and discussion into a readable map of research themes, product framing, policy posture, launch narratives, and market attention.."},{"subject":"Agentic Inference Optimization Faster Than Sota","predicate":"has source host","object":"baseten.co","text":"Agentic Inference Optimization Faster Than Sota has source host baseten.co."},{"subject":"Agentic Inference Optimization Faster Than Sota","predicate":"has lab","object":"Baseten","text":"Agentic Inference Optimization Faster Than Sota has lab Baseten."},{"subject":"Agentic Inference Optimization Faster Than Sota","predicate":"has signal desk","object":"talking","text":"Agentic Inference Optimization Faster Than Sota has signal desk talking."},{"subject":"Agentic Inference Optimization Faster Than Sota","predicate":"has source host","object":"baseten.co","text":"Agentic Inference Optimization Faster Than Sota has source host baseten.co."},{"subject":"Agentic Inference Optimization Faster Than Sota","predicate":"has notability","object":"Technical post on inference optimization from established AI infra company","text":"Agentic Inference Optimization Faster Than Sota has notability Technical post on inference optimization from established AI infra company."},{"subject":"Agentic Inference Optimization Faster Than Sota","predicate":"has watch term","object":"Eval methodology","text":"Agentic Inference Optimization Faster Than Sota has watch term Eval methodology."},{"subject":"Agentic Inference Optimization Faster Than Sota","predicate":"has watch term","object":"Model card","text":"Agentic Inference Optimization Faster Than Sota has watch term Model card."},{"subject":"Agentic Inference Optimization Faster Than Sota","predicate":"has watch term","object":"Infrastructure","text":"Agentic Inference Optimization Faster Than Sota has watch term Infrastructure."},{"subject":"Agentic Inference Optimization Faster Than Sota","predicate":"has watch term","object":"Agents and tool use","text":"Agentic Inference Optimization Faster Than Sota has watch term Agents and tool use."}]},"intelligence":{"signal_desk":"talking","answer":"Baseten published Agentic Inference Optimization Faster Than Sota. This talking signal gives public context for research themes, product direction, policy, or launch framing. High-signal details: Technical post on inference optimization from established AI infra company · Agentic inference optimization: 50-90% faster engines Announcing our partnership with OpenAI . Read more Model performance Agentic inference optimization: 50-90% faster.... onlylabs links this event to 1 captured evidence page and 6 related writing signals.","semantic_triples":[{"subject":"Baseten","predicate":"published","object":"Agentic Inference Optimization Faster Than Sota","text":"Baseten published Agentic Inference Optimization Faster Than Sota."},{"subject":"Agentic Inference Optimization Faster Than Sota","predicate":"is classified as","object":"writing signal","text":"Agentic Inference Optimization Faster Than Sota is classified as writing signal."},{"subject":"Agentic Inference Optimization Faster Than Sota","predicate":"belongs to","object":"talking desk","text":"Agentic Inference Optimization Faster Than Sota belongs to talking desk."},{"subject":"Agentic Inference Optimization Faster Than Sota","predicate":"has evidence coverage","object":"1 captured evidence page","text":"Agentic Inference Optimization Faster Than Sota has evidence coverage 1 captured evidence page."}]},"signal":{"id":"62020fe3-536a-4733-9a1c-f750baf0026e","url":"https://onlylabs.fyi/signals/62020fe3-536a-4733-9a1c-f750baf0026e","json_url":"https://onlylabs.fyi/signals/62020fe3-536a-4733-9a1c-f750baf0026e/signal.json","source_url":"https://www.baseten.co/blog/agentic-inference-optimization-faster-than-sota/","title":"Agentic Inference Optimization Faster Than Sota","summary":"Baseten published a writing signal. onlylabs watches public writing for research themes, product direction, and model-launch context.","context":null,"kind":{"key":"post_published","label":"Writing"},"org":{"slug":"baseten","name":"Baseten","category":"neocloud"},"occurred_at":"2026-10-02T21:09:34+00:00","first_seen_at":"2026-10-03T00:00:54.440942+00:00","date_source":"sitemap.lastmod","evidence_coverage":{"target_pages":1,"captured_pages":1,"readable_pages":1,"capture_methods":["plain"],"missing_page_urls":[],"failed_page_urls":[],"blocked_page_urls":[],"page_urls":["https://www.baseten.co/blog/agentic-inference-optimization-faster-than-sota/"]},"facets":{},"traction":{"github_stars":null,"hn_points":null,"hn_comments":null,"hn_story_id":null,"hf_downloads":null,"hf_likes":null},"data_radar":null},"primary_evidence_page":{"is_primary":true,"source_match":true,"url":"https://www.baseten.co/blog/agentic-inference-optimization-faster-than-sota/","final_url":"https://www.baseten.co/blog/agentic-inference-optimization-faster-than-sota/","title":"Agentic Inference Optimization Faster Than Sota","http_status":200,"content_type":"text/html; charset=utf-8","capture_method":"plain","fetched_at":"2026-10-03T00:02:34.910318+00:00","bytes":345512,"raw_path":"fdcb78e55793dd6187dd581570ff215f910ecd9456ff847eaa9b8f33e59324bc.html","content_hash":"0dd0e8a11a26560f7bc6b016396e7b6faa309d7d3510e61fc62166f5c9e83960","excerpt_chars":1200,"truncated":true,"excerpt":"Agentic inference optimization: 50-90% faster engines Announcing our partnership with OpenAI . Read more Model performance Agentic inference optimization: 50-90% faster engines Claude Code with Fable 5 built a Qwen 3.6 inference engine that beat vLLM by up to 90% on decode speed and 2.3x on TTFT, using MetaInfer skills on one B200. Authors Shawn Rushefsky Last updated October 2, 2026 Share Baseten is the kind of place where we have Slack channels like #ai-papers-discuss and #model-performance-reading-group , and it was in one of these channels that a paper caught my attention recently: MetaInfer: A Knowledge Only LLM Inference Engine Generator SKILL Toolbox . In it, the authors provide a skills-only framework for building custom inference engines from scratch, claiming their results beat SoTA open solutions like vLLM on common inference performance metrics like time per output token (TPOT). “Skills-only” here means no model post-training, and no specialized harnesses. I’ll admit, I was skeptical, but they provided a repo with the skill toolkit, and we’re still living that unlimited-token good life here, so I thought I’d give it a try on a popular model just to see how it did. With..."},"evidence_pages":[],"related_signals":[{"id":"4c0cbb68-47c1-4803-a2f5-d72d4bf19015","url":"https://onlylabs.fyi/signals/4c0cbb68-47c1-4803-a2f5-d72d4bf19015","source_url":"https://www.baseten.co/blog/safe-open-models-baseten-goodfire/","title":"Safe Open Models Baseten Goodfire","context":null,"kind":{"key":"post_published","label":"Writing"},"org":{"slug":"baseten","name":"Baseten","category":"neocloud"},"occurred_at":"2026-10-09T17:01:47+00:00","first_seen_at":"2026-10-09T20:00:52.666594+00:00","date_source":"sitemap.lastmod"},{"id":"658b9d7c-41fa-4f80-8d86-d06e2b125e60","url":"https://onlylabs.fyi/signals/658b9d7c-41fa-4f80-8d86-d06e2b125e60","source_url":"https://www.baseten.co/blog/what-makes-a-high-quality-nvfp4-quantization/","title":"What Makes A High Quality Nvfp4 Quantization","context":null,"kind":{"key":"post_published","label":"Writing"},"org":{"slug":"baseten","name":"Baseten","category":"neocloud"},"occurred_at":"2026-10-09T14:16:52+00:00","first_seen_at":"2026-10-09T16:00:52.084488+00:00","date_source":"sitemap.lastmod"},{"id":"f8945477-f263-4138-a0de-267443725b59","url":"https://onlylabs.fyi/signals/f8945477-f263-4138-a0de-267443725b59","source_url":"https://www.baseten.co/resources/changelog/deepseek-v41-flash-fast-available-on-baseten/","title":"Deepseek V41 Flash Fast Available On Baseten","context":null,"kind":{"key":"post_published","label":"Writing"},"org":{"slug":"baseten","name":"Baseten","category":"neocloud"},"occurred_at":"2026-10-08T21:27:16+00:00","first_seen_at":"2026-10-09T00:00:51.645057+00:00","date_source":"sitemap.lastmod"},{"id":"dd1e2b13-b670-4a86-af04-b18cd536f3cb","url":"https://onlylabs.fyi/signals/dd1e2b13-b670-4a86-af04-b18cd536f3cb","source_url":"https://www.baseten.co/resources/changelog/baseten-cli-110/","title":"Baseten Cli 110","context":null,"kind":{"key":"post_published","label":"Writing"},"org":{"slug":"baseten","name":"Baseten","category":"neocloud"},"occurred_at":"2026-10-02T16:18:56+00:00","first_seen_at":"2026-10-03T00:00:54.440942+00:00","date_source":"sitemap.lastmod"},{"id":"162d803f-9704-4ac0-b41d-597e80309789","url":"https://onlylabs.fyi/signals/162d803f-9704-4ac0-b41d-597e80309789","source_url":"https://www.baseten.co/blog/baseten-openai-partnership/","title":"Baseten Openai Partnership","context":null,"kind":{"key":"post_published","label":"Writing"},"org":{"slug":"baseten","name":"Baseten","category":"neocloud"},"occurred_at":"2026-09-29T18:08:26+00:00","first_seen_at":"2026-09-30T00:00:51.400417+00:00","date_source":"sitemap.lastmod"},{"id":"36b11619-3f27-4496-a5de-11568f0cc876","url":"https://onlylabs.fyi/signals/36b11619-3f27-4496-a5de-11568f0cc876","source_url":"https://www.baseten.co/blog/announcing-carbon/","title":"Announcing Carbon","context":null,"kind":{"key":"post_published","label":"Writing"},"org":{"slug":"baseten","name":"Baseten","category":"neocloud"},"occurred_at":"2026-09-28T09:09:42+00:00","first_seen_at":"2026-09-28T12:00:58.178108+00:00","date_source":"sitemap.lastmod"}]}