{"schema_version":"onlylabs.public_signal.v1","title":"StepFun Fork: stepfun-ai/llama.cpp","description":"StepFun fork signal with public source context, captured evidence pages, related signals, and category-scoped analysis context.","url":"https://onlylabs.fyi/signals/411e46af-07c9-427d-8522-f0502d830c66","json_url":"https://onlylabs.fyi/signals/411e46af-07c9-427d-8522-f0502d830c66/signal.json","generated_at":"2026-06-11T02:43:02.998427+00:00","org":{"slug":"stepfun","name":"StepFun","category":"neolab","category_label":"Neolab","dossier_url":"https://onlylabs.fyi/labs/stepfun","dossier_json_url":"https://onlylabs.fyi/labs/stepfun/dossier.json"},"related_urls":{"signal":"https://onlylabs.fyi/signals/411e46af-07c9-427d-8522-f0502d830c66","signal_json":"https://onlylabs.fyi/signals/411e46af-07c9-427d-8522-f0502d830c66/signal.json","source":"https://github.com/stepfun-ai/llama.cpp","lab_dossier":"https://onlylabs.fyi/labs/stepfun","lab_dossier_json":"https://onlylabs.fyi/labs/stepfun/dossier.json","analysis":"https://onlylabs.fyi/analysis/stepfun","analysis_json":"https://onlylabs.fyi/analysis/stepfun/analysis.json","analysis_evidence_json":"https://onlylabs.fyi/analysis/stepfun/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":"https://onlylabs.fyi/topics/forks","topic_signals_json":"https://onlylabs.fyi/topics/forks/signals.json?category=neolab","topic_feed":"https://onlylabs.fyi/topics/forks/feed.xml?category=neolab","data_business":null},"answer_pack":{"answer":"StepFun forked stepfun-ai/llama.cpp (forked from ggml-org/llama.cpp). This fork signal points to upstream code the lab may be inspecting, patching, or building on. High-signal details: repo stepfun-ai/llama.cpp · parent ggml-org/llama.cpp · Routine fork with minimal traction. onlylabs links this event to 1 captured evidence page and 1 related fork signal.","signal_desk":"forks","source_context":{"source_url":"https://github.com/stepfun-ai/llama.cpp","source_host":"github.com","occurred_at":"2026-03-16T07:20:37+00:00","first_seen_at":"2026-06-05T20:58:53.52612+00:00","date_source":"source","context":"forked from ggml-org/llama.cpp"},"context_markers":[{"label":"Lab","value":"StepFun","source":"signal"},{"label":"Signal desk","value":"forks","source":"signal"},{"label":"Source host","value":"github.com","source":"source"},{"label":"Repository","value":"stepfun-ai/llama.cpp","source":"source"},{"label":"Parent","value":"ggml-org/llama.cpp","source":"source"},{"label":"Stars","value":"5","source":"traction"},{"label":"Notability","value":"Routine fork with minimal traction","source":"signal"},{"label":"Watch term","value":"Model card","source":"model"},{"label":"Watch term","value":"Infrastructure","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/stepfun-ai/llama.cpp"],"related_signals":1,"has_source_url":true,"latest_page_fetched_at":"2026-06-11T02:43:02.998427+00:00"},"data_business":{"matches":false,"lanes":[],"matched_terms":[],"score":null,"reason":null},"agent_handoff":{"signal_json":"https://onlylabs.fyi/signals/411e46af-07c9-427d-8522-f0502d830c66/signal.json","dossier_json":"https://onlylabs.fyi/labs/stepfun/dossier.json","analysis_json":"https://onlylabs.fyi/analysis/stepfun/analysis.json","analysis_evidence_json":"https://onlylabs.fyi/analysis/stepfun/evidence.json","topic_signals_json":"https://onlylabs.fyi/topics/forks/signals.json?category=neolab","topic_feed":"https://onlylabs.fyi/topics/forks/feed.xml?category=neolab","category_signals_json":"https://onlylabs.fyi/signals.json?category=neolab","data_radar_json":null,"opportunities_json":null},"analysis_playbook":{"objective":"Turn fork activity into a map of upstream tools, libraries, model utilities, agent frameworks, and research dependencies being inspected or adapted.","evidence_focus":["forked parent repo","repo owner","language","description","stars","org and recency"],"extraction_questions":["Which upstream projects are repeated across labs?","Which forks point to evals, agents, infrastructure, model tooling, or data pipelines?","Which low-profile forks could precede a release or hiring wave?","Which labs are converging on the same technical adjacency?"],"signal_questions":["What upstream dependency or technical adjacency does this fork reveal?","Which upstream projects are repeated across labs?","Which forks point to evals, agents, infrastructure, model tooling, or data pipelines?","Do the 1 related fork signals show a repeated pattern?"],"output_fields":["org","upstream_repo","language","technical_theme","evidence_url"],"data_business_relevance":"Data-business lane extraction is scoped to frontier labs; for this category, keep conclusions tied to category-specific strategy, source evidence, and follow-up questions.","required_sources":[{"label":"signal_json","url":"https://onlylabs.fyi/signals/411e46af-07c9-427d-8522-f0502d830c66/signal.json","required":true},{"label":"source","url":"https://github.com/stepfun-ai/llama.cpp","required":true},{"label":"dossier_json","url":"https://onlylabs.fyi/labs/stepfun/dossier.json","required":true},{"label":"analysis_evidence_json","url":"https://onlylabs.fyi/analysis/stepfun/evidence.json","required":true},{"label":"topic_signals_json","url":"https://onlylabs.fyi/topics/forks/signals.json?category=neolab","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 StepFun's fork signal \"stepfun-ai/llama.cpp\" for neolab strategy."},"semantic_triples":[{"subject":"StepFun","predicate":"forked","object":"stepfun-ai/llama.cpp","text":"StepFun forked stepfun-ai/llama.cpp."},{"subject":"stepfun-ai/llama.cpp","predicate":"is classified as","object":"fork signal","text":"stepfun-ai/llama.cpp is classified as fork signal."},{"subject":"stepfun-ai/llama.cpp","predicate":"belongs to","object":"forks desk","text":"stepfun-ai/llama.cpp belongs to forks desk."},{"subject":"stepfun-ai/llama.cpp","predicate":"has context","object":"forked from ggml-org/llama.cpp","text":"stepfun-ai/llama.cpp has context forked from ggml-org/llama.cpp."},{"subject":"stepfun-ai/llama.cpp","predicate":"has evidence coverage","object":"1 captured evidence page","text":"stepfun-ai/llama.cpp has evidence coverage 1 captured evidence page."},{"subject":"stepfun-ai/llama.cpp","predicate":"has captured page count","object":"1","text":"stepfun-ai/llama.cpp has captured page count 1."},{"subject":"stepfun-ai/llama.cpp","predicate":"has readable page count","object":"1","text":"stepfun-ai/llama.cpp has readable page count 1."},{"subject":"stepfun-ai/llama.cpp","predicate":"has related signal count","object":"1","text":"stepfun-ai/llama.cpp has related signal count 1."},{"subject":"stepfun-ai/llama.cpp","predicate":"has analysis playbook objective","object":"Turn fork activity into a map of upstream tools, libraries, model utilities, agent frameworks, and research dependencies being inspected or adapted.","text":"stepfun-ai/llama.cpp has analysis playbook objective Turn fork activity into a map of upstream tools, libraries, model utilities, agent frameworks, and research dependencies being inspected or adapted.."},{"subject":"stepfun-ai/llama.cpp","predicate":"has source host","object":"github.com","text":"stepfun-ai/llama.cpp has source host github.com."},{"subject":"stepfun-ai/llama.cpp","predicate":"has lab","object":"StepFun","text":"stepfun-ai/llama.cpp has lab StepFun."},{"subject":"stepfun-ai/llama.cpp","predicate":"has signal desk","object":"forks","text":"stepfun-ai/llama.cpp has signal desk forks."},{"subject":"stepfun-ai/llama.cpp","predicate":"has source host","object":"github.com","text":"stepfun-ai/llama.cpp has source host github.com."},{"subject":"stepfun-ai/llama.cpp","predicate":"has repository","object":"stepfun-ai/llama.cpp","text":"stepfun-ai/llama.cpp has repository stepfun-ai/llama.cpp."},{"subject":"stepfun-ai/llama.cpp","predicate":"has parent","object":"ggml-org/llama.cpp","text":"stepfun-ai/llama.cpp has parent ggml-org/llama.cpp."},{"subject":"stepfun-ai/llama.cpp","predicate":"has stars","object":"5","text":"stepfun-ai/llama.cpp has stars 5."},{"subject":"stepfun-ai/llama.cpp","predicate":"has notability","object":"Routine fork with minimal traction","text":"stepfun-ai/llama.cpp has notability Routine fork with minimal traction."},{"subject":"stepfun-ai/llama.cpp","predicate":"has watch term","object":"Model card","text":"stepfun-ai/llama.cpp has watch term Model card."}]},"intelligence":{"signal_desk":"forks","answer":"StepFun forked stepfun-ai/llama.cpp (forked from ggml-org/llama.cpp). This fork signal points to upstream code the lab may be inspecting, patching, or building on. High-signal details: repo stepfun-ai/llama.cpp · parent ggml-org/llama.cpp · Routine fork with minimal traction. onlylabs links this event to 1 captured evidence page and 1 related fork signal.","semantic_triples":[{"subject":"StepFun","predicate":"forked","object":"stepfun-ai/llama.cpp","text":"StepFun forked stepfun-ai/llama.cpp."},{"subject":"stepfun-ai/llama.cpp","predicate":"is classified as","object":"fork signal","text":"stepfun-ai/llama.cpp is classified as fork signal."},{"subject":"stepfun-ai/llama.cpp","predicate":"belongs to","object":"forks desk","text":"stepfun-ai/llama.cpp belongs to forks desk."},{"subject":"stepfun-ai/llama.cpp","predicate":"has context","object":"forked from ggml-org/llama.cpp","text":"stepfun-ai/llama.cpp has context forked from ggml-org/llama.cpp."},{"subject":"stepfun-ai/llama.cpp","predicate":"has evidence coverage","object":"1 captured evidence page","text":"stepfun-ai/llama.cpp has evidence coverage 1 captured evidence page."}]},"signal":{"id":"411e46af-07c9-427d-8522-f0502d830c66","url":"https://onlylabs.fyi/signals/411e46af-07c9-427d-8522-f0502d830c66","json_url":"https://onlylabs.fyi/signals/411e46af-07c9-427d-8522-f0502d830c66/signal.json","source_url":"https://github.com/stepfun-ai/llama.cpp","title":"stepfun-ai/llama.cpp","summary":"StepFun forked upstream code. onlylabs watches forks for tooling, infrastructure, research dependencies, and product-adjacent work.","context":"forked from ggml-org/llama.cpp","kind":{"key":"repo_forked","label":"Fork"},"org":{"slug":"stepfun","name":"StepFun","category":"neolab"},"occurred_at":"2026-03-16T07:20:37+00:00","first_seen_at":"2026-06-05T20:58:53.52612+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/stepfun-ai/llama.cpp"]},"facets":{"repo":"stepfun-ai/llama.cpp","parent":"ggml-org/llama.cpp"},"traction":{"github_stars":5,"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/stepfun-ai/llama.cpp","final_url":"https://github.com/stepfun-ai/llama.cpp","title":"stepfun-ai/llama.cpp repository metadata","http_status":200,"content_type":"application/json","capture_method":"plain","fetched_at":"2026-06-11T02:43:02.998427+00:00","bytes":49842,"raw_path":"207fb739c668976b056a17668ce60787df95de29500d4c9a837de2de049e5145.json","content_hash":"bd71fbd362b6b385d7b2c3a5ef0fff6a670eb1c0e6aa35a251b3c039d8e72f0c","excerpt_chars":1200,"truncated":true,"excerpt":"stepfun-ai/llama.cpp Description: LLM inference in C/C++ Language: C++ License: MIT Stars: 5 Forks: 1 Open issues: 1 Created: 2026-03-16T07:20:37Z Pushed: 2026-06-09T12:23:15Z Default branch: master Fork: yes Parent repository: ggml-org/llama.cpp Archived: no README: llama.cpp ![llama](https://user-images.githubusercontent.com/1991296/230134379-7181e485-c521-4d23-a0d6-f7b3b61ba524.png) [![License: MIT](https://img.shields.io/badge/license-MIT-blue.svg)](https://opensource.org/licenses/MIT) [![Release](https://img.shields.io/github/v/release/ggml-org/llama.cpp)](https://github.com/ggml-org/llama.cpp/releases) [![Server](https://github.com/ggml-org/llama.cpp/actions/workflows/server.yml/badge.svg)](https://github.com/ggml-org/llama.cpp/actions/workflows/server.yml) [Manifesto](https://github.com/ggml-org/llama.cpp/discussions/205) / [ggml](https://github.com/ggml-org/ggml) / [ops](https://github.com/ggml-org/llama.cpp/blob/master/docs/ops.md) LLM inference in C/C++ Recent API changes - [Changelog for `libllama` API](https://github.com/ggml-org/llama.cpp/issues/9289) - [Changelog for `llama-server` REST API](https://github.com/ggml-org/llama.cpp/issues/9291) Hot topics - **Hugging..."},"evidence_pages":[{"url":"https://github.com/stepfun-ai/llama.cpp","final_url":"https://github.com/stepfun-ai/llama.cpp","title":"stepfun-ai/llama.cpp repository metadata","http_status":200,"content_type":"application/json","capture_method":"plain","fetched_at":"2026-06-11T02:43:02.998427+00:00","bytes":49842,"raw_path":"207fb739c668976b056a17668ce60787df95de29500d4c9a837de2de049e5145.json","content_hash":"bd71fbd362b6b385d7b2c3a5ef0fff6a670eb1c0e6aa35a251b3c039d8e72f0c","excerpt_chars":1200,"truncated":true,"excerpt":"stepfun-ai/llama.cpp Description: LLM inference in C/C++ Language: C++ License: MIT Stars: 5 Forks: 1 Open issues: 1 Created: 2026-03-16T07:20:37Z Pushed: 2026-06-09T12:23:15Z Default branch: master Fork: yes Parent repository: ggml-org/llama.cpp Archived: no README: llama.cpp ![llama](https://user-images.githubusercontent.com/1991296/230134379-7181e485-c521-4d23-a0d6-f7b3b61ba524.png) [![License: MIT](https://img.shields.io/badge/license-MIT-blue.svg)](https://opensource.org/licenses/MIT) [![Release](https://img.shields.io/github/v/release/ggml-org/llama.cpp)](https://github.com/ggml-org/llama.cpp/releases) [![Server](https://github.com/ggml-org/llama.cpp/actions/workflows/server.yml/badge.svg)](https://github.com/ggml-org/llama.cpp/actions/workflows/server.yml) [Manifesto](https://github.com/ggml-org/llama.cpp/discussions/205) / [ggml](https://github.com/ggml-org/ggml) / [ops](https://github.com/ggml-org/llama.cpp/blob/master/docs/ops.md) LLM inference in C/C++ Recent API changes - [Changelog for `libllama` API](https://github.com/ggml-org/llama.cpp/issues/9289) - [Changelog for `llama-server` REST API](https://github.com/ggml-org/llama.cpp/issues/9291) Hot topics - **Hugging..."}],"related_signals":[{"id":"a14be8d5-87fe-47a5-8e4a-1ace1cebce42","url":"https://onlylabs.fyi/signals/a14be8d5-87fe-47a5-8e4a-1ace1cebce42","source_url":"https://github.com/stepfun-ai/vllm","title":"stepfun-ai/vllm","context":"forked from vllm-project/vllm","kind":{"key":"repo_forked","label":"Fork"},"org":{"slug":"stepfun","name":"StepFun","category":"neolab"},"occurred_at":"2025-02-18T07:53:03+00:00","first_seen_at":"2026-06-05T20:58:53.52612+00:00","date_source":"source"}]}