{"schema_version":"onlylabs.public_signal.v1","title":"NVIDIA Release: NVIDIA/TensorRT-LLM v1.4.0rc1","description":"NVIDIA release signal with public source context, captured evidence pages, related signals, and data-business radar classification.","url":"https://onlylabs.fyi/signals/e6a2184c-2bb1-427c-ae42-47b192e3d78b","json_url":"https://onlylabs.fyi/signals/e6a2184c-2bb1-427c-ae42-47b192e3d78b/signal.json","generated_at":"2026-10-25T11:15:18.380Z","evidence_latest_fetched_at":"2026-10-22T07:01:28.905623+00:00","signal_first_seen_at":"2026-10-22T07:00:44.425038+00:00","org":{"slug":"nvidia","name":"NVIDIA","category":"frontier-lab","category_label":"Frontier lab","dossier_url":"https://onlylabs.fyi/labs/nvidia","dossier_json_url":"https://onlylabs.fyi/labs/nvidia/dossier.json"},"related_urls":{"signal":"https://onlylabs.fyi/signals/e6a2184c-2bb1-427c-ae42-47b192e3d78b","signal_json":"https://onlylabs.fyi/signals/e6a2184c-2bb1-427c-ae42-47b192e3d78b/signal.json","source":"https://github.com/NVIDIA/TensorRT-LLM/releases/tag/v1.4.0rc1","lab_dossier":"https://onlylabs.fyi/labs/nvidia","lab_dossier_json":"https://onlylabs.fyi/labs/nvidia/dossier.json","analysis":"https://onlylabs.fyi/analysis/nvidia","analysis_json":"https://onlylabs.fyi/analysis/nvidia/analysis.json","analysis_evidence_json":"https://onlylabs.fyi/analysis/nvidia/evidence.json","category":"https://onlylabs.fyi/frontier","category_json":"https://onlylabs.fyi/frontier.json","category_feed":"https://onlylabs.fyi/frontier/feed.xml","category_signals_json":"https://onlylabs.fyi/signals.json","topic":"https://onlylabs.fyi/topics/releases","topic_signals_json":"https://onlylabs.fyi/topics/releases/signals.json","topic_feed":"https://onlylabs.fyi/topics/releases/feed.xml","data_business":null},"answer_pack":{"answer":"NVIDIA published NVIDIA/TensorRT-LLM v1.4.0rc1 (NVIDIA/TensorRT-LLM). This release signal is evidence of what shipped, changed, or was packaged for users. High-signal details: Notable inference library release candidate · v1.4.0rc1 Repository: NVIDIA/TensorRT-LLM Tag: v1.4.0rc1 Published: 2026-10-22T01:38:13Z Prerelease: yes Release notes: Highlights - Known Issues - Disaggregated serving.... onlylabs links this event to 1 captured evidence page and 6 related release signals.","signal_desk":"releases","source_context":{"source_url":"https://github.com/NVIDIA/TensorRT-LLM/releases/tag/v1.4.0rc1","source_host":"github.com","occurred_at":"2026-10-22T01:38:13+00:00","first_seen_at":"2026-10-22T07:00:44.425038+00:00","date_source":"source","context":"NVIDIA/TensorRT-LLM"},"context_markers":[{"label":"Lab","value":"NVIDIA","source":"signal"},{"label":"Signal desk","value":"releases","source":"signal"},{"label":"Source host","value":"github.com","source":"source"},{"label":"Repository","value":"NVIDIA/TensorRT-LLM","source":"source"},{"label":"Release","value":"v1.4.0rc1","source":"source"},{"label":"Notability","value":"Notable inference library release candidate","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":"Safety and alignment","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://github.com/NVIDIA/TensorRT-LLM/releases/tag/v1.4.0rc1"],"related_signals":6,"has_source_url":true,"latest_page_fetched_at":"2026-10-22T07:01:28.905623+00:00"},"data_business":{"matches":false,"lanes":[],"matched_terms":[],"score":null,"reason":null},"agent_handoff":{"signal_json":"https://onlylabs.fyi/signals/e6a2184c-2bb1-427c-ae42-47b192e3d78b/signal.json","dossier_json":"https://onlylabs.fyi/labs/nvidia/dossier.json","analysis_json":"https://onlylabs.fyi/analysis/nvidia/analysis.json","analysis_evidence_json":"https://onlylabs.fyi/analysis/nvidia/evidence.json","topic_signals_json":"https://onlylabs.fyi/topics/releases/signals.json","topic_feed":"https://onlylabs.fyi/topics/releases/feed.xml","category_signals_json":"https://onlylabs.fyi/signals.json","data_radar_json":null,"opportunities_json":null},"analysis_playbook":{"objective":"Turn model cards, repository releases, and launch artifacts into a current view of what shipped and what changed.","evidence_focus":["model card","release note","version or tag","pipeline tag","license","downloads, likes, stars, and linked papers"],"extraction_questions":["What actually shipped, and through which public artifact?","Which releases include inspectable model, repo, paper, or package evidence?","Which launches create new eval, data, infra, or deployment needs?","Which shipped signals are missing captured page context?"],"signal_questions":["What changed in this release, and what downstream data or infrastructure need could it create?","What actually shipped, and through which public artifact?","Which releases include inspectable model, repo, paper, or package evidence?","Do the 6 related release signals show a repeated pattern?"],"output_fields":["org","release_type","artifact","traction","data_business_lane","evidence_url"],"data_business_relevance":"Release signals show the hard edge of lab execution and help connect data-business opportunities to concrete model, repo, and deployment changes.","required_sources":[{"label":"signal_json","url":"https://onlylabs.fyi/signals/e6a2184c-2bb1-427c-ae42-47b192e3d78b/signal.json","required":true},{"label":"source","url":"https://github.com/NVIDIA/TensorRT-LLM/releases/tag/v1.4.0rc1","required":true},{"label":"dossier_json","url":"https://onlylabs.fyi/labs/nvidia/dossier.json","required":true},{"label":"analysis_evidence_json","url":"https://onlylabs.fyi/analysis/nvidia/evidence.json","required":true},{"label":"topic_signals_json","url":"https://onlylabs.fyi/topics/releases/signals.json","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 NVIDIA's release signal \"NVIDIA/TensorRT-LLM v1.4.0rc1\" for frontier lab strategy."},"semantic_triples":[{"subject":"NVIDIA","predicate":"released","object":"NVIDIA/TensorRT-LLM v1.4.0rc1","text":"NVIDIA released NVIDIA/TensorRT-LLM v1.4.0rc1."},{"subject":"NVIDIA/TensorRT-LLM v1.4.0rc1","predicate":"is classified as","object":"release signal","text":"NVIDIA/TensorRT-LLM v1.4.0rc1 is classified as release signal."},{"subject":"NVIDIA/TensorRT-LLM v1.4.0rc1","predicate":"belongs to","object":"releases desk","text":"NVIDIA/TensorRT-LLM v1.4.0rc1 belongs to releases desk."},{"subject":"NVIDIA/TensorRT-LLM v1.4.0rc1","predicate":"has context","object":"NVIDIA/TensorRT-LLM","text":"NVIDIA/TensorRT-LLM v1.4.0rc1 has context NVIDIA/TensorRT-LLM."},{"subject":"NVIDIA/TensorRT-LLM v1.4.0rc1","predicate":"has evidence coverage","object":"1 captured evidence page","text":"NVIDIA/TensorRT-LLM v1.4.0rc1 has evidence coverage 1 captured evidence page."},{"subject":"NVIDIA/TensorRT-LLM v1.4.0rc1","predicate":"has captured page count","object":"1","text":"NVIDIA/TensorRT-LLM v1.4.0rc1 has captured page count 1."},{"subject":"NVIDIA/TensorRT-LLM v1.4.0rc1","predicate":"has readable page count","object":"1","text":"NVIDIA/TensorRT-LLM v1.4.0rc1 has readable page count 1."},{"subject":"NVIDIA/TensorRT-LLM v1.4.0rc1","predicate":"has related signal count","object":"6","text":"NVIDIA/TensorRT-LLM v1.4.0rc1 has related signal count 6."},{"subject":"NVIDIA/TensorRT-LLM v1.4.0rc1","predicate":"has analysis playbook objective","object":"Turn model cards, repository releases, and launch artifacts into a current view of what shipped and what changed.","text":"NVIDIA/TensorRT-LLM v1.4.0rc1 has analysis playbook objective Turn model cards, repository releases, and launch artifacts into a current view of what shipped and what changed.."},{"subject":"NVIDIA/TensorRT-LLM v1.4.0rc1","predicate":"has source host","object":"github.com","text":"NVIDIA/TensorRT-LLM v1.4.0rc1 has source host github.com."},{"subject":"NVIDIA/TensorRT-LLM v1.4.0rc1","predicate":"has lab","object":"NVIDIA","text":"NVIDIA/TensorRT-LLM v1.4.0rc1 has lab NVIDIA."},{"subject":"NVIDIA/TensorRT-LLM v1.4.0rc1","predicate":"has signal desk","object":"releases","text":"NVIDIA/TensorRT-LLM v1.4.0rc1 has signal desk releases."},{"subject":"NVIDIA/TensorRT-LLM v1.4.0rc1","predicate":"has source host","object":"github.com","text":"NVIDIA/TensorRT-LLM v1.4.0rc1 has source host github.com."},{"subject":"NVIDIA/TensorRT-LLM v1.4.0rc1","predicate":"has repository","object":"NVIDIA/TensorRT-LLM","text":"NVIDIA/TensorRT-LLM v1.4.0rc1 has repository NVIDIA/TensorRT-LLM."},{"subject":"NVIDIA/TensorRT-LLM v1.4.0rc1","predicate":"has release","object":"v1.4.0rc1","text":"NVIDIA/TensorRT-LLM v1.4.0rc1 has release v1.4.0rc1."},{"subject":"NVIDIA/TensorRT-LLM v1.4.0rc1","predicate":"has notability","object":"Notable inference library release candidate","text":"NVIDIA/TensorRT-LLM v1.4.0rc1 has notability Notable inference library release candidate."},{"subject":"NVIDIA/TensorRT-LLM v1.4.0rc1","predicate":"has watch term","object":"Eval methodology","text":"NVIDIA/TensorRT-LLM v1.4.0rc1 has watch term Eval methodology."},{"subject":"NVIDIA/TensorRT-LLM v1.4.0rc1","predicate":"has watch term","object":"Model card","text":"NVIDIA/TensorRT-LLM v1.4.0rc1 has watch term Model card."}]},"intelligence":{"signal_desk":"releases","answer":"NVIDIA published NVIDIA/TensorRT-LLM v1.4.0rc1 (NVIDIA/TensorRT-LLM). This release signal is evidence of what shipped, changed, or was packaged for users. High-signal details: Notable inference library release candidate · v1.4.0rc1 Repository: NVIDIA/TensorRT-LLM Tag: v1.4.0rc1 Published: 2026-10-22T01:38:13Z Prerelease: yes Release notes: Highlights - Known Issues - Disaggregated serving.... onlylabs links this event to 1 captured evidence page and 6 related release signals.","semantic_triples":[{"subject":"NVIDIA","predicate":"released","object":"NVIDIA/TensorRT-LLM v1.4.0rc1","text":"NVIDIA released NVIDIA/TensorRT-LLM v1.4.0rc1."},{"subject":"NVIDIA/TensorRT-LLM v1.4.0rc1","predicate":"is classified as","object":"release signal","text":"NVIDIA/TensorRT-LLM v1.4.0rc1 is classified as release signal."},{"subject":"NVIDIA/TensorRT-LLM v1.4.0rc1","predicate":"belongs to","object":"releases desk","text":"NVIDIA/TensorRT-LLM v1.4.0rc1 belongs to releases desk."},{"subject":"NVIDIA/TensorRT-LLM v1.4.0rc1","predicate":"has context","object":"NVIDIA/TensorRT-LLM","text":"NVIDIA/TensorRT-LLM v1.4.0rc1 has context NVIDIA/TensorRT-LLM."},{"subject":"NVIDIA/TensorRT-LLM v1.4.0rc1","predicate":"has evidence coverage","object":"1 captured evidence page","text":"NVIDIA/TensorRT-LLM v1.4.0rc1 has evidence coverage 1 captured evidence page."}]},"signal":{"id":"e6a2184c-2bb1-427c-ae42-47b192e3d78b","url":"https://onlylabs.fyi/signals/e6a2184c-2bb1-427c-ae42-47b192e3d78b","json_url":"https://onlylabs.fyi/signals/e6a2184c-2bb1-427c-ae42-47b192e3d78b/signal.json","source_url":"https://github.com/NVIDIA/TensorRT-LLM/releases/tag/v1.4.0rc1","title":"NVIDIA/TensorRT-LLM v1.4.0rc1","summary":"NVIDIA published release notes. onlylabs watches releases for what actually shipped.","context":"NVIDIA/TensorRT-LLM","kind":{"key":"release","label":"Release"},"org":{"slug":"nvidia","name":"NVIDIA","category":"frontier-lab"},"occurred_at":"2026-10-22T01:38:13+00:00","first_seen_at":"2026-10-22T07:00:44.425038+00:00","date_source":"source","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://github.com/NVIDIA/TensorRT-LLM/releases/tag/v1.4.0rc1"]},"facets":{"repo":"NVIDIA/TensorRT-LLM"},"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://github.com/NVIDIA/TensorRT-LLM/releases/tag/v1.4.0rc1","final_url":"https://github.com/NVIDIA/TensorRT-LLM/releases/tag/v1.4.0rc1","title":"NVIDIA/TensorRT-LLM v1.4.0rc1","http_status":200,"content_type":"application/json","capture_method":"plain","fetched_at":"2026-10-22T07:01:28.905623+00:00","bytes":42481,"raw_path":"9afad8327bb3ca864a751afe81ef0b1971f96b1e0d117a2358e41f3a05fd2a13.json","content_hash":"b587551887844596f3834d16d2927658f69c616c47061bbcf5ed7281d1096dc8","excerpt_chars":1200,"truncated":true,"excerpt":"v1.4.0rc1 Repository: NVIDIA/TensorRT-LLM Tag: v1.4.0rc1 Published: 2026-10-22T01:38:13Z Prerelease: yes Release notes: Highlights - Known Issues - Disaggregated serving with the default Python KV cache transceiver may fail generation requests with a KV cache transfer error after streaming requests are cancelled (observed on A100). - The OpenAI JSON-schema serving example (examples/serve/openai_completion_client_json_schema.py) may return an unbounded response with Qwen3 models. - Model Support - Add DeepSeek-V4.1-Flash support #19727 - Support NVFP4 GLM-5.3-Flash checkpoints #20127 - Add Qwen3.8-Flash-Next NVFP4 as an experimental Modeling V2 target #20143 - Support LiLiCorr draft checkpoints in DFlash #19856 - Remove the automatic W4A16 fallback for Nemotron-H NVFP4 checkpoints on Hopper #15772 - API - Default to KV cache manager V2 and the Python KV cache transceiver (BREAKING) #17495 - Remove unused LlmRequest fields (BREAKING) #19967 - Replace the C++ ArrayView API with std::span #20205 - Select Modeling V2 through LLM configuration and arguments #20077 - Publish serving configuration schemas #19906 - Add a KV cache lending API for transfer backends #19722 - Expose native KV..."},"evidence_pages":[],"related_signals":[{"id":"62db52b2-862b-4724-84cd-88e589f1edda","url":"https://onlylabs.fyi/signals/62db52b2-862b-4724-84cd-88e589f1edda","source_url":"https://github.com/NVIDIA/nvcf/releases/tag/deploy/helm/cloud-functions/v1.27.3","title":"NVIDIA/nvcf deploy/helm/cloud-functions/v1.27.3","context":"NVIDIA/nvcf","kind":{"key":"release","label":"Release"},"org":{"slug":"nvidia","name":"NVIDIA","category":"frontier-lab"},"occurred_at":"2026-10-24T22:31:07+00:00","first_seen_at":"2026-10-25T07:00:42.566418+00:00","date_source":"source"},{"id":"67bbe31f-8b76-4179-9747-24b624ef401a","url":"https://onlylabs.fyi/signals/67bbe31f-8b76-4179-9747-24b624ef401a","source_url":"https://github.com/NVIDIA/nvcf/releases/tag/deploy/stacks/nvcf-compute-plane/v1.0.2","title":"NVIDIA/nvcf deploy/stacks/nvcf-compute-plane/v1.0.2","context":"NVIDIA/nvcf","kind":{"key":"release","label":"Release"},"org":{"slug":"nvidia","name":"NVIDIA","category":"frontier-lab"},"occurred_at":"2026-10-24T22:15:42+00:00","first_seen_at":"2026-10-25T07:00:42.566418+00:00","date_source":"source"},{"id":"8565d6c9-f4fd-48fd-95dc-d7a182d2fbaf","url":"https://onlylabs.fyi/signals/8565d6c9-f4fd-48fd-95dc-d7a182d2fbaf","source_url":"https://github.com/NVIDIA/nvcf/releases/tag/deploy/helm/cloud-functions/v1.32.1","title":"NVIDIA/nvcf deploy/helm/cloud-functions/v1.32.1","context":"NVIDIA/nvcf","kind":{"key":"release","label":"Release"},"org":{"slug":"nvidia","name":"NVIDIA","category":"frontier-lab"},"occurred_at":"2026-10-24T21:54:20+00:00","first_seen_at":"2026-10-25T07:00:42.566418+00:00","date_source":"source"},{"id":"52f2464d-3146-4115-a8a2-d49376f94d9a","url":"https://onlylabs.fyi/signals/52f2464d-3146-4115-a8a2-d49376f94d9a","source_url":"https://github.com/NVIDIA/nvcf/releases/tag/src/compute-plane-services/byoo-otel-collector/v0.160.0-nv-0.2.8","title":"NVIDIA/nvcf src/compute-plane-services/byoo-otel-collector/v0.160.0-nv-0.2.8","context":"NVIDIA/nvcf","kind":{"key":"release","label":"Release"},"org":{"slug":"nvidia","name":"NVIDIA","category":"frontier-lab"},"occurred_at":"2026-10-24T17:48:16+00:00","first_seen_at":"2026-10-25T07:00:42.566418+00:00","date_source":"source"},{"id":"ffba2496-2e95-482b-8999-2983e9818798","url":"https://onlylabs.fyi/signals/ffba2496-2e95-482b-8999-2983e9818798","source_url":"https://github.com/NVIDIA/nvcf/releases/tag/deploy/stacks/self-managed/v1.0.6","title":"NVIDIA/nvcf deploy/stacks/self-managed/v1.0.6","context":"NVIDIA/nvcf","kind":{"key":"release","label":"Release"},"org":{"slug":"nvidia","name":"NVIDIA","category":"frontier-lab"},"occurred_at":"2026-10-24T17:10:18+00:00","first_seen_at":"2026-10-25T07:00:42.566418+00:00","date_source":"source"},{"id":"fab919a6-bd13-4e27-8c6a-5e80ae809651","url":"https://onlylabs.fyi/signals/fab919a6-bd13-4e27-8c6a-5e80ae809651","source_url":"https://github.com/NVIDIA/pytorch-windows-ci/releases/tag/woa-nightly-20261024-r40083756426","title":"NVIDIA/pytorch-windows-ci woa-nightly-20261024-r40083756426","context":"NVIDIA/pytorch-windows-ci","kind":{"key":"release","label":"Release"},"org":{"slug":"nvidia","name":"NVIDIA","category":"frontier-lab"},"occurred_at":"2026-10-24T16:38:50+00:00","first_seen_at":"2026-10-25T07:00:42.566418+00:00","date_source":"source"}]}