{"schema_version":"onlylabs.public_signal.v1","title":"NVIDIA Release: NVIDIA/TensorRT-LLM v1.3.0rc14","description":"NVIDIA release signal with public source context, captured evidence pages, related signals, and data-business radar classification.","url":"https://onlylabs.fyi/signals/7288956a-d685-480c-be3c-07c45e6419c4","json_url":"https://onlylabs.fyi/signals/7288956a-d685-480c-be3c-07c45e6419c4/signal.json","generated_at":"2026-06-11T03:42:38.258267+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/7288956a-d685-480c-be3c-07c45e6419c4","signal_json":"https://onlylabs.fyi/signals/7288956a-d685-480c-be3c-07c45e6419c4/signal.json","source":"https://github.com/NVIDIA/TensorRT-LLM/releases/tag/v1.3.0rc14","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 v1.3.0rc14 (NVIDIA/TensorRT-LLM). This release signal is evidence of what shipped, changed, or was packaged for users. High-signal details: Notable release candidate for key LLM inference library · v1.3.0rc14 Repository: NVIDIA/TensorRT-LLM Tag: v1.3.0rc14 Published: 2026-05-07T05:55:19Z Prerelease: yes Release notes: Highlights - Model Support - Add prefix caching.... 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/v1.3.0rc14","source_host":"github.com","occurred_at":"2026-05-07T05:55:19+00:00","first_seen_at":"2026-06-06T01:49:43.157024+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":"v1.3.0rc14","source":"source"},{"label":"Notability","value":"Notable release candidate for key LLM inference library","source":"signal"},{"label":"Watch term","value":"Infrastructure","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/v1.3.0rc14"],"related_signals":6,"has_source_url":true,"latest_page_fetched_at":"2026-06-11T03:42:38.258267+00:00"},"data_business":{"matches":false,"lanes":[],"matched_terms":[],"score":null,"reason":null},"agent_handoff":{"signal_json":"https://onlylabs.fyi/signals/7288956a-d685-480c-be3c-07c45e6419c4/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/7288956a-d685-480c-be3c-07c45e6419c4/signal.json","required":true},{"label":"source","url":"https://github.com/NVIDIA/TensorRT-LLM/releases/tag/v1.3.0rc14","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 v1.3.0rc14\" for frontier lab strategy."},"semantic_triples":[{"subject":"NVIDIA","predicate":"released","object":"NVIDIA/TensorRT-LLM v1.3.0rc14","text":"NVIDIA released NVIDIA/TensorRT-LLM v1.3.0rc14."},{"subject":"NVIDIA/TensorRT-LLM v1.3.0rc14","predicate":"is classified as","object":"release signal","text":"NVIDIA/TensorRT-LLM v1.3.0rc14 is classified as release signal."},{"subject":"NVIDIA/TensorRT-LLM v1.3.0rc14","predicate":"belongs to","object":"releases desk","text":"NVIDIA/TensorRT-LLM v1.3.0rc14 belongs to releases desk."},{"subject":"NVIDIA/TensorRT-LLM v1.3.0rc14","predicate":"has context","object":"NVIDIA/TensorRT-LLM","text":"NVIDIA/TensorRT-LLM v1.3.0rc14 has context NVIDIA/TensorRT-LLM."},{"subject":"NVIDIA/TensorRT-LLM v1.3.0rc14","predicate":"has evidence coverage","object":"1 captured evidence page","text":"NVIDIA/TensorRT-LLM v1.3.0rc14 has evidence coverage 1 captured evidence page."},{"subject":"NVIDIA/TensorRT-LLM v1.3.0rc14","predicate":"has captured page count","object":"1","text":"NVIDIA/TensorRT-LLM v1.3.0rc14 has captured page count 1."},{"subject":"NVIDIA/TensorRT-LLM v1.3.0rc14","predicate":"has readable page count","object":"1","text":"NVIDIA/TensorRT-LLM v1.3.0rc14 has readable page count 1."},{"subject":"NVIDIA/TensorRT-LLM v1.3.0rc14","predicate":"has related signal count","object":"6","text":"NVIDIA/TensorRT-LLM v1.3.0rc14 has related signal count 6."},{"subject":"NVIDIA/TensorRT-LLM v1.3.0rc14","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 v1.3.0rc14 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 v1.3.0rc14","predicate":"has source host","object":"github.com","text":"NVIDIA/TensorRT-LLM v1.3.0rc14 has source host github.com."},{"subject":"NVIDIA/TensorRT-LLM v1.3.0rc14","predicate":"has lab","object":"NVIDIA","text":"NVIDIA/TensorRT-LLM v1.3.0rc14 has lab NVIDIA."},{"subject":"NVIDIA/TensorRT-LLM v1.3.0rc14","predicate":"has signal desk","object":"releases","text":"NVIDIA/TensorRT-LLM v1.3.0rc14 has signal desk releases."},{"subject":"NVIDIA/TensorRT-LLM v1.3.0rc14","predicate":"has source host","object":"github.com","text":"NVIDIA/TensorRT-LLM v1.3.0rc14 has source host github.com."},{"subject":"NVIDIA/TensorRT-LLM v1.3.0rc14","predicate":"has repository","object":"NVIDIA/TensorRT-LLM","text":"NVIDIA/TensorRT-LLM v1.3.0rc14 has repository NVIDIA/TensorRT-LLM."},{"subject":"NVIDIA/TensorRT-LLM v1.3.0rc14","predicate":"has release","object":"v1.3.0rc14","text":"NVIDIA/TensorRT-LLM v1.3.0rc14 has release v1.3.0rc14."},{"subject":"NVIDIA/TensorRT-LLM v1.3.0rc14","predicate":"has notability","object":"Notable release candidate for key LLM inference library","text":"NVIDIA/TensorRT-LLM v1.3.0rc14 has notability Notable release candidate for key LLM inference library."},{"subject":"NVIDIA/TensorRT-LLM v1.3.0rc14","predicate":"has watch term","object":"Infrastructure","text":"NVIDIA/TensorRT-LLM v1.3.0rc14 has watch term Infrastructure."}]},"intelligence":{"signal_desk":"releases","answer":"NVIDIA published NVIDIA/TensorRT-LLM v1.3.0rc14 (NVIDIA/TensorRT-LLM). This release signal is evidence of what shipped, changed, or was packaged for users. High-signal details: Notable release candidate for key LLM inference library · v1.3.0rc14 Repository: NVIDIA/TensorRT-LLM Tag: v1.3.0rc14 Published: 2026-05-07T05:55:19Z Prerelease: yes Release notes: Highlights - Model Support - Add prefix caching.... onlylabs links this event to 1 captured evidence page and 6 related release signals.","semantic_triples":[{"subject":"NVIDIA","predicate":"released","object":"NVIDIA/TensorRT-LLM v1.3.0rc14","text":"NVIDIA released NVIDIA/TensorRT-LLM v1.3.0rc14."},{"subject":"NVIDIA/TensorRT-LLM v1.3.0rc14","predicate":"is classified as","object":"release signal","text":"NVIDIA/TensorRT-LLM v1.3.0rc14 is classified as release signal."},{"subject":"NVIDIA/TensorRT-LLM v1.3.0rc14","predicate":"belongs to","object":"releases desk","text":"NVIDIA/TensorRT-LLM v1.3.0rc14 belongs to releases desk."},{"subject":"NVIDIA/TensorRT-LLM v1.3.0rc14","predicate":"has context","object":"NVIDIA/TensorRT-LLM","text":"NVIDIA/TensorRT-LLM v1.3.0rc14 has context NVIDIA/TensorRT-LLM."},{"subject":"NVIDIA/TensorRT-LLM v1.3.0rc14","predicate":"has evidence coverage","object":"1 captured evidence page","text":"NVIDIA/TensorRT-LLM v1.3.0rc14 has evidence coverage 1 captured evidence page."}]},"signal":{"id":"7288956a-d685-480c-be3c-07c45e6419c4","url":"https://onlylabs.fyi/signals/7288956a-d685-480c-be3c-07c45e6419c4","json_url":"https://onlylabs.fyi/signals/7288956a-d685-480c-be3c-07c45e6419c4/signal.json","source_url":"https://github.com/NVIDIA/TensorRT-LLM/releases/tag/v1.3.0rc14","title":"NVIDIA/TensorRT-LLM v1.3.0rc14","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":"2026-05-07T05:55:19+00:00","first_seen_at":"2026-06-06T01:49:43.157024+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/v1.3.0rc14"]},"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":{"url":"https://github.com/NVIDIA/TensorRT-LLM/releases/tag/v1.3.0rc14","final_url":"https://github.com/NVIDIA/TensorRT-LLM/releases/tag/v1.3.0rc14","title":"NVIDIA/TensorRT-LLM v1.3.0rc14","http_status":200,"content_type":"application/json","capture_method":"plain","fetched_at":"2026-06-11T03:42:38.258267+00:00","bytes":28430,"raw_path":"11b58633021e4c8d7886debd73011ecf9b9a427070abdedfd64c070e5962059e.json","content_hash":"3a16d3d8b0f0b35f8324648f0450efcd2557d19f0930b3e1ee06b8c29c2693c5","excerpt_chars":1200,"truncated":true,"excerpt":"v1.3.0rc14 Repository: NVIDIA/TensorRT-LLM Tag: v1.3.0rc14 Published: 2026-05-07T05:55:19Z Prerelease: yes Release notes: Highlights - Model Support - Add prefix caching for Mamba hybrid models including Qwen3.5 and Nemotron Super V3 (#12185) - Improve Qwen3.5 support with custom MoE routing and dense and NVFP4 weight loading fixes (#13433, #13090, #13716) - Improve Nemotron and Nemotron Nano support with GEMM tuning and multimodal placeholder expansion (#13160, #13069) - Add Wan 2.2 5B TI2V support and refine LTX-2 FP4 stage handling (#13256, #13244) - API - Embed VisualGenParams in DiffusionRequest and simplify generate() inputs (#13313) - Add llm.encode() fast path support for encoder-only models (#12801) - Add per-iteration request-aggregate counters to InflightBatchingStats (#13199) - Add AGSI middleware support for Serve (#13378) - Introduce cancellation support in transceiver v2 (#12734) - Fix Triton backend generation parameter handling for promptIgnoreLength, lengthPenalty, earlyStopping, and early_stopping (#13633, #13692) - Feature - Improve VisualGen serving with fast PNG compression, multi-node diffusion workers, non-contiguous multimodal chunked prefill, and..."},"evidence_pages":[{"url":"https://github.com/NVIDIA/TensorRT-LLM/releases/tag/v1.3.0rc14","final_url":"https://github.com/NVIDIA/TensorRT-LLM/releases/tag/v1.3.0rc14","title":"NVIDIA/TensorRT-LLM v1.3.0rc14","http_status":200,"content_type":"application/json","capture_method":"plain","fetched_at":"2026-06-11T03:42:38.258267+00:00","bytes":28430,"raw_path":"11b58633021e4c8d7886debd73011ecf9b9a427070abdedfd64c070e5962059e.json","content_hash":"3a16d3d8b0f0b35f8324648f0450efcd2557d19f0930b3e1ee06b8c29c2693c5","excerpt_chars":1200,"truncated":true,"excerpt":"v1.3.0rc14 Repository: NVIDIA/TensorRT-LLM Tag: v1.3.0rc14 Published: 2026-05-07T05:55:19Z Prerelease: yes Release notes: Highlights - Model Support - Add prefix caching for Mamba hybrid models including Qwen3.5 and Nemotron Super V3 (#12185) - Improve Qwen3.5 support with custom MoE routing and dense and NVFP4 weight loading fixes (#13433, #13090, #13716) - Improve Nemotron and Nemotron Nano support with GEMM tuning and multimodal placeholder expansion (#13160, #13069) - Add Wan 2.2 5B TI2V support and refine LTX-2 FP4 stage handling (#13256, #13244) - API - Embed VisualGenParams in DiffusionRequest and simplify generate() inputs (#13313) - Add llm.encode() fast path support for encoder-only models (#12801) - Add per-iteration request-aggregate counters to InflightBatchingStats (#13199) - Add AGSI middleware support for Serve (#13378) - Introduce cancellation support in transceiver v2 (#12734) - Fix Triton backend generation parameter handling for promptIgnoreLength, lengthPenalty, earlyStopping, and early_stopping (#13633, #13692) - Feature - Improve VisualGen serving with fast PNG compression, multi-node diffusion workers, non-contiguous multimodal chunked prefill, and..."}],"related_signals":[{"id":"45f4cdf4-5665-44fd-b290-c27312411e95","url":"https://onlylabs.fyi/signals/45f4cdf4-5665-44fd-b290-c27312411e95","source_url":"https://github.com/NVIDIA/open-nvdebug/releases/tag/nvdebug-v2.1.0-release","title":"NVIDIA/open-nvdebug nvdebug-v2.1.0-release","context":"NVIDIA/open-nvdebug","kind":{"key":"release","label":"Release"},"org":{"slug":"nvidia","name":"NVIDIA","category":"frontier-lab"},"occurred_at":"2026-06-11T05:57:30+00:00","first_seen_at":"2026-06-11T07:01:14.42859+00:00","date_source":"source"},{"id":"25a9df96-2996-450c-a19b-ac955b7e77b7","url":"https://onlylabs.fyi/signals/25a9df96-2996-450c-a19b-ac955b7e77b7","source_url":"https://github.com/NVIDIA/open-nvdebug/releases/tag/nvdebug-v2.0.0","title":"NVIDIA/open-nvdebug nvdebug-v2.0.0","context":"NVIDIA/open-nvdebug","kind":{"key":"release","label":"Release"},"org":{"slug":"nvidia","name":"NVIDIA","category":"frontier-lab"},"occurred_at":"2026-06-11T05:55:39+00:00","first_seen_at":"2026-06-11T07:01:14.42859+00:00","date_source":"source"},{"id":"837ce80c-4bdb-48fc-947b-8842ace3a199","url":"https://onlylabs.fyi/signals/837ce80c-4bdb-48fc-947b-8842ace3a199","source_url":"https://github.com/NVIDIA/nv-rms-client/releases/tag/v0.9.0-mts-rc02","title":"NVIDIA/nv-rms-client v0.9.0-mts-rc02","context":"NVIDIA/nv-rms-client","kind":{"key":"release","label":"Release"},"org":{"slug":"nvidia","name":"NVIDIA","category":"frontier-lab"},"occurred_at":"2026-06-11T05:19:43+00:00","first_seen_at":"2026-06-11T07:01:14.42859+00:00","date_source":"source"},{"id":"1f40b37a-1570-4da9-b4ed-a722da3acd28","url":"https://onlylabs.fyi/signals/1f40b37a-1570-4da9-b4ed-a722da3acd28","source_url":"https://github.com/NVIDIA/cudnn-frontend/releases/tag/v1.25.0","title":"NVIDIA/cudnn-frontend v1.25.0","context":"NVIDIA/cudnn-frontend","kind":{"key":"release","label":"Release"},"org":{"slug":"nvidia","name":"NVIDIA","category":"frontier-lab"},"occurred_at":"2026-06-10T21:11:51+00:00","first_seen_at":"2026-06-11T07:01:14.42859+00:00","date_source":"source"},{"id":"c5fe1a74-96b4-4f19-a620-d1b63758cdcb","url":"https://onlylabs.fyi/signals/c5fe1a74-96b4-4f19-a620-d1b63758cdcb","source_url":"https://github.com/NVIDIA/nv-rms-client/releases/tag/v0.9.0-mts-rc01","title":"NVIDIA/nv-rms-client v0.9.0-mts-rc01","context":"NVIDIA/nv-rms-client","kind":{"key":"release","label":"Release"},"org":{"slug":"nvidia","name":"NVIDIA","category":"frontier-lab"},"occurred_at":"2026-06-10T19:02:10+00:00","first_seen_at":"2026-06-11T07:01:14.42859+00:00","date_source":"source"},{"id":"565de597-ad94-49ff-91ef-632e549ba88d","url":"https://onlylabs.fyi/signals/565de597-ad94-49ff-91ef-632e549ba88d","source_url":"https://github.com/NVIDIA/elements/releases/tag/%40nvidia-elements/styles-v2.0.2","title":"NVIDIA/elements @nvidia-elements/styles-v2.0.2","context":"NVIDIA/elements","kind":{"key":"release","label":"Release"},"org":{"slug":"nvidia","name":"NVIDIA","category":"frontier-lab"},"occurred_at":"2026-06-10T18:51:17+00:00","first_seen_at":"2026-06-11T07:01:14.42859+00:00","date_source":"source"}]}