{"schema_version":"onlylabs.public_signal.v1","title":"NVIDIA Release: NVIDIA/TensorRT-LLM v1.3.0rc18","description":"NVIDIA release signal with public source context, captured evidence pages, related signals, and data-business radar classification.","url":"https://onlylabs.fyi/signals/ce0f4399-15b8-4217-a373-5e5ef4480d51","json_url":"https://onlylabs.fyi/signals/ce0f4399-15b8-4217-a373-5e5ef4480d51/signal.json","generated_at":"2026-06-10T07:04:17.351202+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/ce0f4399-15b8-4217-a373-5e5ef4480d51","signal_json":"https://onlylabs.fyi/signals/ce0f4399-15b8-4217-a373-5e5ef4480d51/signal.json","source":"https://github.com/NVIDIA/TensorRT-LLM/releases/tag/v1.3.0rc18","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 v1.3.0rc18 (NVIDIA/TensorRT-LLM). This release signal is evidence of what shipped, changed, or was packaged for users. High-signal details: NVIDIA's library for optimized LLM inference on GPUs. · v1.3.0rc18 Repository: NVIDIA/TensorRT-LLM Tag: v1.3.0rc18 Published: 2026-06-10T00:10:37Z Prerelease: yes Release notes: - Known Issues - DSV3.2 will crash with an IMA.... 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/v1.3.0rc18","source_host":"github.com","occurred_at":"2026-06-10T00:10:37+00:00","first_seen_at":"2026-06-10T07:01:26.094065+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":"v1.3.0rc18","source":"source"},{"label":"Context","value":"NVIDIA's library for optimized LLM inference on GPUs.","source":"signal"},{"label":"Notability","value":"Routine release candidate of an optimization library.","source":"signal"},{"label":"Watch term","value":"Data pipeline","source":"evidence"},{"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/v1.3.0rc18"],"related_signals":6,"has_source_url":true,"latest_page_fetched_at":"2026-06-10T07:04:17.351202+00:00"},"data_business":{"matches":false,"lanes":[],"matched_terms":[],"score":null,"reason":null},"agent_handoff":{"signal_json":"https://onlylabs.fyi/signals/ce0f4399-15b8-4217-a373-5e5ef4480d51/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/ce0f4399-15b8-4217-a373-5e5ef4480d51/signal.json","required":true},{"label":"source","url":"https://github.com/NVIDIA/TensorRT-LLM/releases/tag/v1.3.0rc18","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 v1.3.0rc18\" for frontier lab strategy."},"semantic_triples":[{"subject":"NVIDIA","predicate":"released","object":"NVIDIA/TensorRT-LLM v1.3.0rc18","text":"NVIDIA released NVIDIA/TensorRT-LLM v1.3.0rc18."},{"subject":"NVIDIA/TensorRT-LLM v1.3.0rc18","predicate":"is classified as","object":"release signal","text":"NVIDIA/TensorRT-LLM v1.3.0rc18 is classified as release signal."},{"subject":"NVIDIA/TensorRT-LLM v1.3.0rc18","predicate":"belongs to","object":"releases desk","text":"NVIDIA/TensorRT-LLM v1.3.0rc18 belongs to releases desk."},{"subject":"NVIDIA/TensorRT-LLM v1.3.0rc18","predicate":"has context","object":"NVIDIA/TensorRT-LLM","text":"NVIDIA/TensorRT-LLM v1.3.0rc18 has context NVIDIA/TensorRT-LLM."},{"subject":"NVIDIA/TensorRT-LLM v1.3.0rc18","predicate":"has evidence coverage","object":"1 captured evidence page","text":"NVIDIA/TensorRT-LLM v1.3.0rc18 has evidence coverage 1 captured evidence page."},{"subject":"NVIDIA/TensorRT-LLM v1.3.0rc18","predicate":"has captured page count","object":"1","text":"NVIDIA/TensorRT-LLM v1.3.0rc18 has captured page count 1."},{"subject":"NVIDIA/TensorRT-LLM v1.3.0rc18","predicate":"has readable page count","object":"1","text":"NVIDIA/TensorRT-LLM v1.3.0rc18 has readable page count 1."},{"subject":"NVIDIA/TensorRT-LLM v1.3.0rc18","predicate":"has related signal count","object":"6","text":"NVIDIA/TensorRT-LLM v1.3.0rc18 has related signal count 6."},{"subject":"NVIDIA/TensorRT-LLM v1.3.0rc18","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 v1.3.0rc18 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 v1.3.0rc18","predicate":"has source host","object":"github.com","text":"NVIDIA/TensorRT-LLM v1.3.0rc18 has source host github.com."},{"subject":"NVIDIA/TensorRT-LLM v1.3.0rc18","predicate":"has lab","object":"NVIDIA","text":"NVIDIA/TensorRT-LLM v1.3.0rc18 has lab NVIDIA."},{"subject":"NVIDIA/TensorRT-LLM v1.3.0rc18","predicate":"has signal desk","object":"releases","text":"NVIDIA/TensorRT-LLM v1.3.0rc18 has signal desk releases."},{"subject":"NVIDIA/TensorRT-LLM v1.3.0rc18","predicate":"has source host","object":"github.com","text":"NVIDIA/TensorRT-LLM v1.3.0rc18 has source host github.com."},{"subject":"NVIDIA/TensorRT-LLM v1.3.0rc18","predicate":"has repository","object":"NVIDIA/TensorRT-LLM","text":"NVIDIA/TensorRT-LLM v1.3.0rc18 has repository NVIDIA/TensorRT-LLM."},{"subject":"NVIDIA/TensorRT-LLM v1.3.0rc18","predicate":"has release","object":"v1.3.0rc18","text":"NVIDIA/TensorRT-LLM v1.3.0rc18 has release v1.3.0rc18."},{"subject":"NVIDIA/TensorRT-LLM v1.3.0rc18","predicate":"has context","object":"NVIDIA's library for optimized LLM inference on GPUs.","text":"NVIDIA/TensorRT-LLM v1.3.0rc18 has context NVIDIA's library for optimized LLM inference on GPUs.."},{"subject":"NVIDIA/TensorRT-LLM v1.3.0rc18","predicate":"has notability","object":"Routine release candidate of an optimization library.","text":"NVIDIA/TensorRT-LLM v1.3.0rc18 has notability Routine release candidate of an optimization library.."},{"subject":"NVIDIA/TensorRT-LLM v1.3.0rc18","predicate":"has watch term","object":"Data pipeline","text":"NVIDIA/TensorRT-LLM v1.3.0rc18 has watch term Data pipeline."}]},"intelligence":{"signal_desk":"releases","answer":"NVIDIA published NVIDIA/TensorRT-LLM v1.3.0rc18 (NVIDIA/TensorRT-LLM). This release signal is evidence of what shipped, changed, or was packaged for users. High-signal details: NVIDIA's library for optimized LLM inference on GPUs. · v1.3.0rc18 Repository: NVIDIA/TensorRT-LLM Tag: v1.3.0rc18 Published: 2026-06-10T00:10:37Z Prerelease: yes Release notes: - Known Issues - DSV3.2 will crash with an IMA.... onlylabs links this event to 1 captured evidence page and 6 related release signals.","semantic_triples":[{"subject":"NVIDIA","predicate":"released","object":"NVIDIA/TensorRT-LLM v1.3.0rc18","text":"NVIDIA released NVIDIA/TensorRT-LLM v1.3.0rc18."},{"subject":"NVIDIA/TensorRT-LLM v1.3.0rc18","predicate":"is classified as","object":"release signal","text":"NVIDIA/TensorRT-LLM v1.3.0rc18 is classified as release signal."},{"subject":"NVIDIA/TensorRT-LLM v1.3.0rc18","predicate":"belongs to","object":"releases desk","text":"NVIDIA/TensorRT-LLM v1.3.0rc18 belongs to releases desk."},{"subject":"NVIDIA/TensorRT-LLM v1.3.0rc18","predicate":"has context","object":"NVIDIA/TensorRT-LLM","text":"NVIDIA/TensorRT-LLM v1.3.0rc18 has context NVIDIA/TensorRT-LLM."},{"subject":"NVIDIA/TensorRT-LLM v1.3.0rc18","predicate":"has evidence coverage","object":"1 captured evidence page","text":"NVIDIA/TensorRT-LLM v1.3.0rc18 has evidence coverage 1 captured evidence page."}]},"signal":{"id":"ce0f4399-15b8-4217-a373-5e5ef4480d51","url":"https://onlylabs.fyi/signals/ce0f4399-15b8-4217-a373-5e5ef4480d51","json_url":"https://onlylabs.fyi/signals/ce0f4399-15b8-4217-a373-5e5ef4480d51/signal.json","source_url":"https://github.com/NVIDIA/TensorRT-LLM/releases/tag/v1.3.0rc18","title":"NVIDIA/TensorRT-LLM v1.3.0rc18","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":"2026-06-10T00:10:37+00:00","first_seen_at":"2026-06-10T07:01:26.094065+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/v1.3.0rc18"]},"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/v1.3.0rc18","final_url":"https://github.com/NVIDIA/TensorRT-LLM/releases/tag/v1.3.0rc18","title":"NVIDIA/TensorRT-LLM v1.3.0rc18","http_status":200,"content_type":"application/json","capture_method":"plain","fetched_at":"2026-06-10T07:04:17.351202+00:00","bytes":27411,"raw_path":"68dda5745316ef70f48b9bb4aa66a75cb0973b8c5acdc4acc16d18974c463fae.json","content_hash":"05c5df8d3718ecdd8bd58121947a00a1d6eb7292ac8d39faade8994b4ecb0ce7","excerpt_chars":1200,"truncated":true,"excerpt":"v1.3.0rc18 Repository: NVIDIA/TensorRT-LLM Tag: v1.3.0rc18 Published: 2026-06-10T00:10:37Z Prerelease: yes Release notes: - Known Issues - DSV3.2 will crash with an IMA in various long-running perf tests on GB200/GB300 when the CuteDSL MoE backend is used. Work around this issue by using another MoE backend. - Model Support - Support Nemotron-H NVFP4 checkpoint on Hopper (#14775) - Add Qwen image support (#13449) - Support Step-3.7-Flash model (#14711) - Add Cosmos3-Nano and Cosmos3-Super support (#14824) - Add AFMoE Trinity support (#13148) - API - Add logprobs_simple_format option to return logprobs as a flat `list[float]` (#13972) - `trtllm-serve`, `trtllm-eval`, `trtllm-bench`: Make CLI flags take precedence over `--config` / `--extra_llm_api_options` YAML (#14812) - Feature - Upgrade NIXL to v1.0.1 and UCX to 1.21 (#14436) - Refactor DWDP from CUDA IPC to CUDA VMM + MNNVL (#14453) - Enable FlashInfer GDN decoding kernel for Qwen3.5 (#13645) - Add per-expert LoRA support with Cutlass backend (#14801) - Reduce OpenAI stream postprocess overhead (#14708) - Add encoder CUDA graph support to `llm.encode()` (#14326) - Use a Triton kernel for C++ mamba hybrid state update (#14869) -..."},"evidence_pages":[{"url":"https://github.com/NVIDIA/TensorRT-LLM/releases/tag/v1.3.0rc18","final_url":"https://github.com/NVIDIA/TensorRT-LLM/releases/tag/v1.3.0rc18","title":"NVIDIA/TensorRT-LLM v1.3.0rc18","http_status":200,"content_type":"application/json","capture_method":"plain","fetched_at":"2026-06-10T07:04:17.351202+00:00","bytes":27411,"raw_path":"68dda5745316ef70f48b9bb4aa66a75cb0973b8c5acdc4acc16d18974c463fae.json","content_hash":"05c5df8d3718ecdd8bd58121947a00a1d6eb7292ac8d39faade8994b4ecb0ce7","excerpt_chars":1200,"truncated":true,"excerpt":"v1.3.0rc18 Repository: NVIDIA/TensorRT-LLM Tag: v1.3.0rc18 Published: 2026-06-10T00:10:37Z Prerelease: yes Release notes: - Known Issues - DSV3.2 will crash with an IMA in various long-running perf tests on GB200/GB300 when the CuteDSL MoE backend is used. Work around this issue by using another MoE backend. - Model Support - Support Nemotron-H NVFP4 checkpoint on Hopper (#14775) - Add Qwen image support (#13449) - Support Step-3.7-Flash model (#14711) - Add Cosmos3-Nano and Cosmos3-Super support (#14824) - Add AFMoE Trinity support (#13148) - API - Add logprobs_simple_format option to return logprobs as a flat `list[float]` (#13972) - `trtllm-serve`, `trtllm-eval`, `trtllm-bench`: Make CLI flags take precedence over `--config` / `--extra_llm_api_options` YAML (#14812) - Feature - Upgrade NIXL to v1.0.1 and UCX to 1.21 (#14436) - Refactor DWDP from CUDA IPC to CUDA VMM + MNNVL (#14453) - Enable FlashInfer GDN decoding kernel for Qwen3.5 (#13645) - Add per-expert LoRA support with Cutlass backend (#14801) - Reduce OpenAI stream postprocess overhead (#14708) - Add encoder CUDA graph support to `llm.encode()` (#14326) - Use a Triton kernel for C++ mamba hybrid state update (#14869) -..."}],"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"}]}