{"schema_version":"onlylabs.public_signal.v1","title":"OpenBMB (MiniCPM) Repo: OpenBMB/infllmv2_cuda_impl","description":"OpenBMB (MiniCPM) repo signal with public source context, captured evidence pages, related signals, and category-scoped analysis context.","url":"https://onlylabs.fyi/signals/48c69864-2d41-464a-80b9-27e95ecd550a","json_url":"https://onlylabs.fyi/signals/48c69864-2d41-464a-80b9-27e95ecd550a/signal.json","generated_at":"2026-06-11T03:20:39.065623+00:00","org":{"slug":"openbmb","name":"OpenBMB (MiniCPM)","category":"neolab","category_label":"Neolab","dossier_url":"https://onlylabs.fyi/labs/openbmb","dossier_json_url":"https://onlylabs.fyi/labs/openbmb/dossier.json"},"related_urls":{"signal":"https://onlylabs.fyi/signals/48c69864-2d41-464a-80b9-27e95ecd550a","signal_json":"https://onlylabs.fyi/signals/48c69864-2d41-464a-80b9-27e95ecd550a/signal.json","source":"https://github.com/OpenBMB/infllmv2_cuda_impl","lab_dossier":"https://onlylabs.fyi/labs/openbmb","lab_dossier_json":"https://onlylabs.fyi/labs/openbmb/dossier.json","analysis":"https://onlylabs.fyi/analysis/openbmb","analysis_json":"https://onlylabs.fyi/analysis/openbmb/analysis.json","analysis_evidence_json":"https://onlylabs.fyi/analysis/openbmb/evidence.json","category":"https://onlylabs.fyi/neolabs","category_json":"https://onlylabs.fyi/neolabs.json","category_feed":"https://onlylabs.fyi/neolabs/feed.xml","category_signals_json":"https://onlylabs.fyi/signals.json?category=neolab","topic":null,"topic_signals_json":null,"topic_feed":null,"data_business":null},"answer_pack":{"answer":"OpenBMB (MiniCPM) published OpenBMB/infllmv2_cuda_impl (Python). This repository signal exposes tooling, eval, infrastructure, or model-adjacent work before it may appear in a launch post. High-signal details: repo OpenBMB/infllmv2_cuda_impl · language Python · CUDA impl for InfLLMv2, modest traction. onlylabs links this event to 1 captured evidence page and 6 related repo signals.","signal_desk":"repos","source_context":{"source_url":"https://github.com/OpenBMB/infllmv2_cuda_impl","source_host":"github.com","occurred_at":"2025-06-05T15:30:25+00:00","first_seen_at":"2026-06-05T20:58:51.434713+00:00","date_source":"source","context":"Python"},"context_markers":[{"label":"Lab","value":"OpenBMB (MiniCPM)","source":"signal"},{"label":"Signal desk","value":"repos","source":"signal"},{"label":"Source host","value":"github.com","source":"source"},{"label":"Repository","value":"OpenBMB/infllmv2_cuda_impl","source":"source"},{"label":"Language","value":"Python","source":"source"},{"label":"Stars","value":"102","source":"traction"},{"label":"Notability","value":"CUDA impl for InfLLMv2, modest traction","source":"signal"},{"label":"Watch term","value":"Eval methodology","source":"evidence"},{"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/OpenBMB/infllmv2_cuda_impl"],"related_signals":6,"has_source_url":true,"latest_page_fetched_at":"2026-06-11T03:20:39.065623+00:00"},"data_business":{"matches":false,"lanes":[],"matched_terms":[],"score":null,"reason":null},"agent_handoff":{"signal_json":"https://onlylabs.fyi/signals/48c69864-2d41-464a-80b9-27e95ecd550a/signal.json","dossier_json":"https://onlylabs.fyi/labs/openbmb/dossier.json","analysis_json":"https://onlylabs.fyi/analysis/openbmb/analysis.json","analysis_evidence_json":"https://onlylabs.fyi/analysis/openbmb/evidence.json","topic_signals_json":null,"topic_feed":null,"category_signals_json":"https://onlylabs.fyi/signals.json?category=neolab","data_radar_json":null,"opportunities_json":null},"analysis_playbook":{"objective":"Turn new repository signals into early evidence of tooling, eval, infrastructure, model-adjacent, or product work before it appears in polished launch channels.","evidence_focus":["repo name","owner","description","language","stars","source URL","first seen time","data, eval, infra, safety, and product terms"],"extraction_questions":["What technical area does this repository expose?","Does the repo imply eval, data, infrastructure, agent, or deployment work?","Is the repo new evidence for a lab direction that is not yet in writing or releases?","Which related signals should an analyst inspect next?"],"signal_questions":["What does this new repository reveal before a formal announcement exists?","What technical area does this repository expose?","Does the repo imply eval, data, infrastructure, agent, or deployment work?","Do the 6 related repo signals show a repeated pattern?"],"output_fields":["org","repo","technical_theme","evidence_url"],"data_business_relevance":"Data-business lane extraction is scoped to frontier labs; for this category, interpret the repository as source-grounded category strategy evidence.","required_sources":[{"label":"signal_json","url":"https://onlylabs.fyi/signals/48c69864-2d41-464a-80b9-27e95ecd550a/signal.json","required":true},{"label":"source","url":"https://github.com/OpenBMB/infllmv2_cuda_impl","required":true},{"label":"dossier_json","url":"https://onlylabs.fyi/labs/openbmb/dossier.json","required":true},{"label":"analysis_evidence_json","url":"https://onlylabs.fyi/analysis/openbmb/evidence.json","required":true},{"label":"topic_signals_json","url":null,"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 OpenBMB (MiniCPM)'s repo signal \"OpenBMB/infllmv2_cuda_impl\" for neolab strategy."},"semantic_triples":[{"subject":"OpenBMB (MiniCPM)","predicate":"published repo","object":"OpenBMB/infllmv2_cuda_impl","text":"OpenBMB (MiniCPM) published repo OpenBMB/infllmv2_cuda_impl."},{"subject":"OpenBMB/infllmv2_cuda_impl","predicate":"is classified as","object":"repo signal","text":"OpenBMB/infllmv2_cuda_impl is classified as repo signal."},{"subject":"OpenBMB/infllmv2_cuda_impl","predicate":"belongs to","object":"repos desk","text":"OpenBMB/infllmv2_cuda_impl belongs to repos desk."},{"subject":"OpenBMB/infllmv2_cuda_impl","predicate":"has context","object":"Python","text":"OpenBMB/infllmv2_cuda_impl has context Python."},{"subject":"OpenBMB/infllmv2_cuda_impl","predicate":"has evidence coverage","object":"1 captured evidence page","text":"OpenBMB/infllmv2_cuda_impl has evidence coverage 1 captured evidence page."},{"subject":"OpenBMB/infllmv2_cuda_impl","predicate":"has captured page count","object":"1","text":"OpenBMB/infllmv2_cuda_impl has captured page count 1."},{"subject":"OpenBMB/infllmv2_cuda_impl","predicate":"has readable page count","object":"1","text":"OpenBMB/infllmv2_cuda_impl has readable page count 1."},{"subject":"OpenBMB/infllmv2_cuda_impl","predicate":"has related signal count","object":"6","text":"OpenBMB/infllmv2_cuda_impl has related signal count 6."},{"subject":"OpenBMB/infllmv2_cuda_impl","predicate":"has analysis playbook objective","object":"Turn new repository signals into early evidence of tooling, eval, infrastructure, model-adjacent, or product work before it appears in polished launch channels.","text":"OpenBMB/infllmv2_cuda_impl has analysis playbook objective Turn new repository signals into early evidence of tooling, eval, infrastructure, model-adjacent, or product work before it appears in polished launch channels.."},{"subject":"OpenBMB/infllmv2_cuda_impl","predicate":"has source host","object":"github.com","text":"OpenBMB/infllmv2_cuda_impl has source host github.com."},{"subject":"OpenBMB/infllmv2_cuda_impl","predicate":"has lab","object":"OpenBMB (MiniCPM)","text":"OpenBMB/infllmv2_cuda_impl has lab OpenBMB (MiniCPM)."},{"subject":"OpenBMB/infllmv2_cuda_impl","predicate":"has signal desk","object":"repos","text":"OpenBMB/infllmv2_cuda_impl has signal desk repos."},{"subject":"OpenBMB/infllmv2_cuda_impl","predicate":"has source host","object":"github.com","text":"OpenBMB/infllmv2_cuda_impl has source host github.com."},{"subject":"OpenBMB/infllmv2_cuda_impl","predicate":"has repository","object":"OpenBMB/infllmv2_cuda_impl","text":"OpenBMB/infllmv2_cuda_impl has repository OpenBMB/infllmv2_cuda_impl."},{"subject":"OpenBMB/infllmv2_cuda_impl","predicate":"has language","object":"Python","text":"OpenBMB/infllmv2_cuda_impl has language Python."},{"subject":"OpenBMB/infllmv2_cuda_impl","predicate":"has stars","object":"102","text":"OpenBMB/infllmv2_cuda_impl has stars 102."},{"subject":"OpenBMB/infllmv2_cuda_impl","predicate":"has notability","object":"CUDA impl for InfLLMv2, modest traction","text":"OpenBMB/infllmv2_cuda_impl has notability CUDA impl for InfLLMv2, modest traction."},{"subject":"OpenBMB/infllmv2_cuda_impl","predicate":"has watch term","object":"Eval methodology","text":"OpenBMB/infllmv2_cuda_impl has watch term Eval methodology."}]},"intelligence":{"signal_desk":"repos","answer":"OpenBMB (MiniCPM) published OpenBMB/infllmv2_cuda_impl (Python). This repository signal exposes tooling, eval, infrastructure, or model-adjacent work before it may appear in a launch post. High-signal details: repo OpenBMB/infllmv2_cuda_impl · language Python · CUDA impl for InfLLMv2, modest traction. onlylabs links this event to 1 captured evidence page and 6 related repo signals.","semantic_triples":[{"subject":"OpenBMB (MiniCPM)","predicate":"published repo","object":"OpenBMB/infllmv2_cuda_impl","text":"OpenBMB (MiniCPM) published repo OpenBMB/infllmv2_cuda_impl."},{"subject":"OpenBMB/infllmv2_cuda_impl","predicate":"is classified as","object":"repo signal","text":"OpenBMB/infllmv2_cuda_impl is classified as repo signal."},{"subject":"OpenBMB/infllmv2_cuda_impl","predicate":"belongs to","object":"repos desk","text":"OpenBMB/infllmv2_cuda_impl belongs to repos desk."},{"subject":"OpenBMB/infllmv2_cuda_impl","predicate":"has context","object":"Python","text":"OpenBMB/infllmv2_cuda_impl has context Python."},{"subject":"OpenBMB/infllmv2_cuda_impl","predicate":"has evidence coverage","object":"1 captured evidence page","text":"OpenBMB/infllmv2_cuda_impl has evidence coverage 1 captured evidence page."}]},"signal":{"id":"48c69864-2d41-464a-80b9-27e95ecd550a","url":"https://onlylabs.fyi/signals/48c69864-2d41-464a-80b9-27e95ecd550a","json_url":"https://onlylabs.fyi/signals/48c69864-2d41-464a-80b9-27e95ecd550a/signal.json","source_url":"https://github.com/OpenBMB/infllmv2_cuda_impl","title":"OpenBMB/infllmv2_cuda_impl","summary":"OpenBMB (MiniCPM) published a new repository. onlylabs watches repos for tooling, eval, infra, and model-adjacent work.","context":"Python","kind":{"key":"repo_new","label":"Repo"},"org":{"slug":"openbmb","name":"OpenBMB (MiniCPM)","category":"neolab"},"occurred_at":"2025-06-05T15:30:25+00:00","first_seen_at":"2026-06-05T20:58:51.434713+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/OpenBMB/infllmv2_cuda_impl"]},"facets":{"repo":"OpenBMB/infllmv2_cuda_impl","language":"Python"},"traction":{"github_stars":102,"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/OpenBMB/infllmv2_cuda_impl","final_url":"https://github.com/OpenBMB/infllmv2_cuda_impl","title":"OpenBMB/infllmv2_cuda_impl repository metadata","http_status":200,"content_type":"application/json","capture_method":"plain","fetched_at":"2026-06-11T03:20:39.065623+00:00","bytes":17100,"raw_path":"21a8f339bb5a4d24d7a6c2ed86c2a1c4b290cf11f00b2b943fab009160e09223.json","content_hash":"d919b0171f0c67da520a47e4eb40483de9e3989707a2866eeaf1c54e33a75e69","excerpt_chars":1200,"truncated":true,"excerpt":"OpenBMB/infllmv2_cuda_impl Language: Python Stars: 102 Forks: 12 Open issues: 0 Created: 2025-06-05T15:30:25Z Pushed: 2026-02-11T10:59:17Z Default branch: main Fork: no Archived: no README: InfLLM V2 CUDA Kernel Implementation This repository contains the optimized CUDA kernel implementation for **InfLLM V2's Two-Stage Sparse Attention Mechanism**. Our implementation provides high-performance kernels for both Stage 1 (Top-K Context Selection) and Stage 2 (Sparse Attention Computation), enabling Large Language Models (LLMs) to efficiently process long contexts with trainable sparse patterns. Overview InfLLM V2 introduces a novel two-stage approach for efficient long-context processing: - **Stage 1: Top-K Context Selection**: Block scoring and aggregation using semantic kernels (kernel computes and aggregates scores, selection performed externally) - **Stage 2: Sparse Attention Computation**: Attention calculation on selected blocks This CUDA kernel implementation includes both stages, providing: - Optimized relevance score computation and aggregation for Stage 1 (Top-K selection performed externally) - Efficient sparse attention on selected blocks for Stage 2 - Significant..."},"evidence_pages":[{"url":"https://github.com/OpenBMB/infllmv2_cuda_impl","final_url":"https://github.com/OpenBMB/infllmv2_cuda_impl","title":"OpenBMB/infllmv2_cuda_impl repository metadata","http_status":200,"content_type":"application/json","capture_method":"plain","fetched_at":"2026-06-11T03:20:39.065623+00:00","bytes":17100,"raw_path":"21a8f339bb5a4d24d7a6c2ed86c2a1c4b290cf11f00b2b943fab009160e09223.json","content_hash":"d919b0171f0c67da520a47e4eb40483de9e3989707a2866eeaf1c54e33a75e69","excerpt_chars":1200,"truncated":true,"excerpt":"OpenBMB/infllmv2_cuda_impl Language: Python Stars: 102 Forks: 12 Open issues: 0 Created: 2025-06-05T15:30:25Z Pushed: 2026-02-11T10:59:17Z Default branch: main Fork: no Archived: no README: InfLLM V2 CUDA Kernel Implementation This repository contains the optimized CUDA kernel implementation for **InfLLM V2's Two-Stage Sparse Attention Mechanism**. Our implementation provides high-performance kernels for both Stage 1 (Top-K Context Selection) and Stage 2 (Sparse Attention Computation), enabling Large Language Models (LLMs) to efficiently process long contexts with trainable sparse patterns. Overview InfLLM V2 introduces a novel two-stage approach for efficient long-context processing: - **Stage 1: Top-K Context Selection**: Block scoring and aggregation using semantic kernels (kernel computes and aggregates scores, selection performed externally) - **Stage 2: Sparse Attention Computation**: Attention calculation on selected blocks This CUDA kernel implementation includes both stages, providing: - Optimized relevance score computation and aggregation for Stage 1 (Top-K selection performed externally) - Efficient sparse attention on selected blocks for Stage 2 - Significant..."}],"related_signals":[{"id":"f409d6eb-9f25-4cb4-8684-3c0300d920cb","url":"https://onlylabs.fyi/signals/f409d6eb-9f25-4cb4-8684-3c0300d920cb","source_url":"https://github.com/OpenBMB/AceBench","title":"OpenBMB/AceBench","context":"Python","kind":{"key":"repo_new","label":"Repo"},"org":{"slug":"openbmb","name":"OpenBMB (MiniCPM)","category":"neolab"},"occurred_at":"2026-06-07T07:34:14+00:00","first_seen_at":"2026-06-08T07:00:32.626037+00:00","date_source":"source"},{"id":"09fa79c2-c357-4b35-9137-3382d7b781fe","url":"https://onlylabs.fyi/signals/09fa79c2-c357-4b35-9137-3382d7b781fe","source_url":"https://github.com/OpenBMB/PilotDeck","title":"OpenBMB/PilotDeck","context":"TypeScript","kind":{"key":"repo_new","label":"Repo"},"org":{"slug":"openbmb","name":"OpenBMB (MiniCPM)","category":"neolab"},"occurred_at":"2026-05-22T06:50:28+00:00","first_seen_at":"2026-06-05T20:58:51.434713+00:00","date_source":"source"},{"id":"7bb917a1-5397-4dea-9822-9e930c5c7be3","url":"https://onlylabs.fyi/signals/7bb917a1-5397-4dea-9822-9e930c5c7be3","source_url":"https://github.com/OpenBMB/MiniCPM-Desk-Pet","title":"OpenBMB/MiniCPM-Desk-Pet","context":"JavaScript","kind":{"key":"repo_new","label":"Repo"},"org":{"slug":"openbmb","name":"OpenBMB (MiniCPM)","category":"neolab"},"occurred_at":"2026-05-18T13:08:37+00:00","first_seen_at":"2026-06-05T20:58:51.434713+00:00","date_source":"source"},{"id":"f4e5394e-af13-4293-a2b4-89c6d0df2b54","url":"https://onlylabs.fyi/signals/f4e5394e-af13-4293-a2b4-89c6d0df2b54","source_url":"https://github.com/OpenBMB/Omni-DuplexEval","title":"OpenBMB/Omni-DuplexEval","context":"Python","kind":{"key":"repo_new","label":"Repo"},"org":{"slug":"openbmb","name":"OpenBMB (MiniCPM)","category":"neolab"},"occurred_at":"2026-05-15T09:44:36+00:00","first_seen_at":"2026-06-05T20:58:51.434713+00:00","date_source":"source"},{"id":"3b4dec65-36de-4552-a00b-2c4920646acc","url":"https://onlylabs.fyi/signals/3b4dec65-36de-4552-a00b-2c4920646acc","source_url":"https://github.com/OpenBMB/ForgeTrain","title":"OpenBMB/ForgeTrain","context":"Python","kind":{"key":"repo_new","label":"Repo"},"org":{"slug":"openbmb","name":"OpenBMB (MiniCPM)","category":"neolab"},"occurred_at":"2026-05-14T08:01:19+00:00","first_seen_at":"2026-06-05T20:58:51.434713+00:00","date_source":"source"},{"id":"dc2c1782-3073-4882-8dda-1887de471b5b","url":"https://onlylabs.fyi/signals/dc2c1782-3073-4882-8dda-1887de471b5b","source_url":"https://github.com/OpenBMB/voxcpm2-demopage","title":"OpenBMB/voxcpm2-demopage","context":"JavaScript","kind":{"key":"repo_new","label":"Repo"},"org":{"slug":"openbmb","name":"OpenBMB (MiniCPM)","category":"neolab"},"occurred_at":"2026-04-06T06:59:02+00:00","first_seen_at":"2026-06-05T20:58:51.434713+00:00","date_source":"source"}]}