{"schema_version":"onlylabs.public_signal.v1","title":"NVIDIA Release: NVIDIA/TensorRT-LLM v1.3.0rc16","description":"NVIDIA release signal with public source context, captured evidence pages, related signals, and data-business radar classification.","url":"https://onlylabs.fyi/signals/ed2dd4c6-16a7-4663-8b32-ff2502e64002","json_url":"https://onlylabs.fyi/signals/ed2dd4c6-16a7-4663-8b32-ff2502e64002/signal.json","generated_at":"2026-06-11T03:39:03.570983+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/ed2dd4c6-16a7-4663-8b32-ff2502e64002","signal_json":"https://onlylabs.fyi/signals/ed2dd4c6-16a7-4663-8b32-ff2502e64002/signal.json","source":"https://github.com/NVIDIA/TensorRT-LLM/releases/tag/v1.3.0rc16","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 v1.3.0rc16 (NVIDIA/TensorRT-LLM). This release signal is evidence of what shipped, changed, or was packaged for users. High-signal details: Major release candidate for LLM inference optimization by NVIDIA. · v1.3.0rc16 Repository: NVIDIA/TensorRT-LLM Tag: v1.3.0rc16 Published: 2026-05-26T08:08:12Z Prerelease: yes Release notes: Highlights - Model Support - Add Gemma4.... 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/v1.3.0rc16","source_host":"github.com","occurred_at":"2026-05-26T08:08:12+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":"v1.3.0rc16","source":"source"},{"label":"Notability","value":"Major release candidate for LLM inference optimization by NVIDIA.","source":"signal"},{"label":"Watch term","value":"Eval methodology","source":"evidence"},{"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/v1.3.0rc16"],"related_signals":6,"has_source_url":true,"latest_page_fetched_at":"2026-06-11T03:39:03.570983+00:00"},"data_business":{"matches":false,"lanes":[],"matched_terms":[],"score":null,"reason":null},"agent_handoff":{"signal_json":"https://onlylabs.fyi/signals/ed2dd4c6-16a7-4663-8b32-ff2502e64002/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/ed2dd4c6-16a7-4663-8b32-ff2502e64002/signal.json","required":true},{"label":"source","url":"https://github.com/NVIDIA/TensorRT-LLM/releases/tag/v1.3.0rc16","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 v1.3.0rc16\" for frontier lab strategy."},"semantic_triples":[{"subject":"NVIDIA","predicate":"released","object":"NVIDIA/TensorRT-LLM v1.3.0rc16","text":"NVIDIA released NVIDIA/TensorRT-LLM v1.3.0rc16."},{"subject":"NVIDIA/TensorRT-LLM v1.3.0rc16","predicate":"is classified as","object":"release signal","text":"NVIDIA/TensorRT-LLM v1.3.0rc16 is classified as release signal."},{"subject":"NVIDIA/TensorRT-LLM v1.3.0rc16","predicate":"belongs to","object":"releases desk","text":"NVIDIA/TensorRT-LLM v1.3.0rc16 belongs to releases desk."},{"subject":"NVIDIA/TensorRT-LLM v1.3.0rc16","predicate":"has context","object":"NVIDIA/TensorRT-LLM","text":"NVIDIA/TensorRT-LLM v1.3.0rc16 has context NVIDIA/TensorRT-LLM."},{"subject":"NVIDIA/TensorRT-LLM v1.3.0rc16","predicate":"has evidence coverage","object":"1 captured evidence page","text":"NVIDIA/TensorRT-LLM v1.3.0rc16 has evidence coverage 1 captured evidence page."},{"subject":"NVIDIA/TensorRT-LLM v1.3.0rc16","predicate":"has captured page count","object":"1","text":"NVIDIA/TensorRT-LLM v1.3.0rc16 has captured page count 1."},{"subject":"NVIDIA/TensorRT-LLM v1.3.0rc16","predicate":"has readable page count","object":"1","text":"NVIDIA/TensorRT-LLM v1.3.0rc16 has readable page count 1."},{"subject":"NVIDIA/TensorRT-LLM v1.3.0rc16","predicate":"has related signal count","object":"6","text":"NVIDIA/TensorRT-LLM v1.3.0rc16 has related signal count 6."},{"subject":"NVIDIA/TensorRT-LLM v1.3.0rc16","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 v1.3.0rc16 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 v1.3.0rc16","predicate":"has source host","object":"github.com","text":"NVIDIA/TensorRT-LLM v1.3.0rc16 has source host github.com."},{"subject":"NVIDIA/TensorRT-LLM v1.3.0rc16","predicate":"has lab","object":"NVIDIA","text":"NVIDIA/TensorRT-LLM v1.3.0rc16 has lab NVIDIA."},{"subject":"NVIDIA/TensorRT-LLM v1.3.0rc16","predicate":"has signal desk","object":"releases","text":"NVIDIA/TensorRT-LLM v1.3.0rc16 has signal desk releases."},{"subject":"NVIDIA/TensorRT-LLM v1.3.0rc16","predicate":"has source host","object":"github.com","text":"NVIDIA/TensorRT-LLM v1.3.0rc16 has source host github.com."},{"subject":"NVIDIA/TensorRT-LLM v1.3.0rc16","predicate":"has repository","object":"NVIDIA/TensorRT-LLM","text":"NVIDIA/TensorRT-LLM v1.3.0rc16 has repository NVIDIA/TensorRT-LLM."},{"subject":"NVIDIA/TensorRT-LLM v1.3.0rc16","predicate":"has release","object":"v1.3.0rc16","text":"NVIDIA/TensorRT-LLM v1.3.0rc16 has release v1.3.0rc16."},{"subject":"NVIDIA/TensorRT-LLM v1.3.0rc16","predicate":"has notability","object":"Major release candidate for LLM inference optimization by NVIDIA.","text":"NVIDIA/TensorRT-LLM v1.3.0rc16 has notability Major release candidate for LLM inference optimization by NVIDIA.."},{"subject":"NVIDIA/TensorRT-LLM v1.3.0rc16","predicate":"has watch term","object":"Eval methodology","text":"NVIDIA/TensorRT-LLM v1.3.0rc16 has watch term Eval methodology."},{"subject":"NVIDIA/TensorRT-LLM v1.3.0rc16","predicate":"has watch term","object":"Infrastructure","text":"NVIDIA/TensorRT-LLM v1.3.0rc16 has watch term Infrastructure."}]},"intelligence":{"signal_desk":"releases","answer":"NVIDIA published NVIDIA/TensorRT-LLM v1.3.0rc16 (NVIDIA/TensorRT-LLM). This release signal is evidence of what shipped, changed, or was packaged for users. High-signal details: Major release candidate for LLM inference optimization by NVIDIA. · v1.3.0rc16 Repository: NVIDIA/TensorRT-LLM Tag: v1.3.0rc16 Published: 2026-05-26T08:08:12Z Prerelease: yes Release notes: Highlights - Model Support - Add Gemma4.... onlylabs links this event to 1 captured evidence page and 6 related release signals.","semantic_triples":[{"subject":"NVIDIA","predicate":"released","object":"NVIDIA/TensorRT-LLM v1.3.0rc16","text":"NVIDIA released NVIDIA/TensorRT-LLM v1.3.0rc16."},{"subject":"NVIDIA/TensorRT-LLM v1.3.0rc16","predicate":"is classified as","object":"release signal","text":"NVIDIA/TensorRT-LLM v1.3.0rc16 is classified as release signal."},{"subject":"NVIDIA/TensorRT-LLM v1.3.0rc16","predicate":"belongs to","object":"releases desk","text":"NVIDIA/TensorRT-LLM v1.3.0rc16 belongs to releases desk."},{"subject":"NVIDIA/TensorRT-LLM v1.3.0rc16","predicate":"has context","object":"NVIDIA/TensorRT-LLM","text":"NVIDIA/TensorRT-LLM v1.3.0rc16 has context NVIDIA/TensorRT-LLM."},{"subject":"NVIDIA/TensorRT-LLM v1.3.0rc16","predicate":"has evidence coverage","object":"1 captured evidence page","text":"NVIDIA/TensorRT-LLM v1.3.0rc16 has evidence coverage 1 captured evidence page."}]},"signal":{"id":"ed2dd4c6-16a7-4663-8b32-ff2502e64002","url":"https://onlylabs.fyi/signals/ed2dd4c6-16a7-4663-8b32-ff2502e64002","json_url":"https://onlylabs.fyi/signals/ed2dd4c6-16a7-4663-8b32-ff2502e64002/signal.json","source_url":"https://github.com/NVIDIA/TensorRT-LLM/releases/tag/v1.3.0rc16","title":"NVIDIA/TensorRT-LLM v1.3.0rc16","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":"2026-05-26T08:08:12+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/v1.3.0rc16"]},"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/v1.3.0rc16","final_url":"https://github.com/NVIDIA/TensorRT-LLM/releases/tag/v1.3.0rc16","title":"NVIDIA/TensorRT-LLM v1.3.0rc16","http_status":200,"content_type":"application/json","capture_method":"plain","fetched_at":"2026-06-11T03:39:03.570983+00:00","bytes":22550,"raw_path":"76c79475675d9cf883ed7f29946da8823f13f56a981a206ce7445623a054b9c0.json","content_hash":"d8f1d024a96ff44af1340773451bff8a0b6ef65219005adf01f9ecec7add5608","excerpt_chars":1200,"truncated":true,"excerpt":"v1.3.0rc16 Repository: NVIDIA/TensorRT-LLM Tag: v1.3.0rc16 Published: 2026-05-26T08:08:12Z Prerelease: yes Release notes: Highlights - Model Support - Add Gemma4 multimodal support with native vision and audio towers (#14300) - Add Qwen3.5 MTP and Qwen3.6-27B-FP8 model support (#12646, #14359) - Add EXAONE-4.5 and Laguna model support (#12873, #13559) - Switch DeepSeek, NemotronH, Qwen3, and Qwen3.5-MoE to sharding-IR canonical models (#13478) - API - Refactor the VisualGenArgs API and registry (#14175) - Drop sink_token_length from the PyTorch attention surface (#14275) - Add OpenAI chat logit bias validation (#13518) - Reject incompatible KV connector configurations at construction time (#13577) - Feature - Add exact multimodal KV block hashing and KV cache reuse probing (#13815, #14333) - Add KV cache manager v2 with Python transceiver updates (#12928) - Add disaggregated serving support with block reuse enabled for hybrid models (#14060) - Add FlashInfer MLA attention backend support and SkipSoftmax sparse attention support for visual generation (#13428, #12947) - Add Ring Attention and unified context parallelism for VisualGen (#13821) - Add legacy and TensorRT-LLM 1.x..."},"evidence_pages":[{"url":"https://github.com/NVIDIA/TensorRT-LLM/releases/tag/v1.3.0rc16","final_url":"https://github.com/NVIDIA/TensorRT-LLM/releases/tag/v1.3.0rc16","title":"NVIDIA/TensorRT-LLM v1.3.0rc16","http_status":200,"content_type":"application/json","capture_method":"plain","fetched_at":"2026-06-11T03:39:03.570983+00:00","bytes":22550,"raw_path":"76c79475675d9cf883ed7f29946da8823f13f56a981a206ce7445623a054b9c0.json","content_hash":"d8f1d024a96ff44af1340773451bff8a0b6ef65219005adf01f9ecec7add5608","excerpt_chars":1200,"truncated":true,"excerpt":"v1.3.0rc16 Repository: NVIDIA/TensorRT-LLM Tag: v1.3.0rc16 Published: 2026-05-26T08:08:12Z Prerelease: yes Release notes: Highlights - Model Support - Add Gemma4 multimodal support with native vision and audio towers (#14300) - Add Qwen3.5 MTP and Qwen3.6-27B-FP8 model support (#12646, #14359) - Add EXAONE-4.5 and Laguna model support (#12873, #13559) - Switch DeepSeek, NemotronH, Qwen3, and Qwen3.5-MoE to sharding-IR canonical models (#13478) - API - Refactor the VisualGenArgs API and registry (#14175) - Drop sink_token_length from the PyTorch attention surface (#14275) - Add OpenAI chat logit bias validation (#13518) - Reject incompatible KV connector configurations at construction time (#13577) - Feature - Add exact multimodal KV block hashing and KV cache reuse probing (#13815, #14333) - Add KV cache manager v2 with Python transceiver updates (#12928) - Add disaggregated serving support with block reuse enabled for hybrid models (#14060) - Add FlashInfer MLA attention backend support and SkipSoftmax sparse attention support for visual generation (#13428, #12947) - Add Ring Attention and unified context parallelism for VisualGen (#13821) - Add legacy and TensorRT-LLM 1.x..."}],"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"}]}