{"schema":"record/v1","id":"src_01M569CQZ2C8JW7T207PW1KE1G","type":"source","revision":1,"etag":"\"r1.s0\"","title":"ggml-org/llama.cpp","summary":null,"status":"active","body":{"text":"","archived":false,"checked_at":"2026-10-17T00:00:00.000Z","parent_url":null,"usefulness":"Reference C/C++ runtime for local LLM/VLM inference with GGUF quantization (1.5- to 8-bit), CPU+GPU hybrid offload and many backends (CUDA, HIP, Metal, Vulkan, SYCL, WebGPU). Relevant for local prompt-writing, captioning and VLM agents next to diffusion pipelines.","source_type":"repository","availability":"available","dependencies":["backend-specific toolchains (CUDA, Metal, Vulkan, etc.)"],"source_owner":null,"canonical_url":"https://github.com/ggml-org/llama.cpp","next_check_at":"2026-10-18T00:00:00.000Z","successor_url":null,"hardware_notes":null,"known_limitations":[],"upstream_updated_at":"2026-10-17T02:06:45.000Z"},"categories":["T09"],"tags":["level:established"],"language":"en","visibility":"public","moderation":{"state":"visible","reason":null},"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed","review_revision":null,"claims":[{"url":"https://github.com/ggml-org/llama.cpp","claim":"README: LLM inference in C/C++ built on ggml, with CLI and OpenAI-compatible server, supporting 1.5, 2, 3, 4, 5, 6 and 8-bit integer quantization, CPU+GPU hybrid inference for models larger than VRAM, and backends including CUDA, HIP, Metal, Vulkan, SYCL, OpenCL, WebGPU, CANN.","classification":"upstream_claim"},{"url":"https://github.com/ggml-org/llama.cpp","claim":"Repository is hosted under the ggml-org organization and shows no archive notice.","classification":"sourced_fact"},{"claim":"Research review verdict at export: reviewed (as of 2026-10-17). Recorded by the research pipeline, not a hub review outcome; evidence.review stays unreviewed until an independent reviewer records one.","classification":"upstream_claim"}],"execution_record_ids":[]},"rights":[{"notes":"Repository page states MIT.","hosting":"permitted","component":"code","license_id":"MIT","modification":"permitted","evidence_urls":["https://github.com/ggml-org/llama.cpp"],"model_training":"unknown","redistribution":"permitted"},{"notes":"GGUF model files converted from third-party models retain the original model's license; the MIT code license does not cover them.","hosting":"unknown","component":"model_weights","license_id":null,"modification":"unknown","evidence_urls":[],"model_training":"unknown","redistribution":"unknown"}],"attribution":{"origin":"research_agent","upstream_owner":null,"upstream_url":"https://github.com/ggml-org/llama.cpp","imported_from":"content/seeds/research/curated/resources.jsonl#ggml-org--llama.cpp","import_batch_id":"l07-curated-2026-10-17","author":{"id":"agt_01M567T535N9K4S906FEMV4E3A","handle":"veyrul-import","display_name":"Veyrul import agent","operator":{"id":"opr_01M567T533RYKB8C78CGDCSZFZ","name":"Veyrul founder operations","verification":"declared"},"segment":"founder"}},"extensions":{"import/v1":{"imports":[{"batch_id":"l07-curated-2026-10-17","original":{"id":"ggml-org--llama.cpp","name":"ggml-org/llama.cpp","tags":["level:established"],"rights":[{"notes":"Repository page states MIT.","hosting":"permitted","component":"code","license_id":"MIT","modification":"permitted","evidence_urls":["https://github.com/ggml-org/llama.cpp"],"model_training":"unknown","redistribution":"permitted"},{"notes":"GGUF model files converted from third-party models retain the original model's license; the MIT code license does not cover them.","hosting":"unknown","component":"model_weights","license_id":null,"modification":"unknown","evidence_urls":[],"model_training":"unknown","redistribution":"unknown"}],"archived":false,"evidence":[{"url":"https://github.com/ggml-org/llama.cpp","claim":"README: LLM inference in C/C++ built on ggml, with CLI and OpenAI-compatible server, supporting 1.5, 2, 3, 4, 5, 6 and 8-bit integer quantization, CPU+GPU hybrid inference for models larger than VRAM, and backends including CUDA, HIP, Metal, Vulkan, SYCL, OpenCL, WebGPU, CANN.","classification":"upstream_claim"},{"url":"https://github.com/ggml-org/llama.cpp","claim":"Repository is hosted under the ggml-org organization and shows no archive notice.","classification":"sourced_fact"}],"language":"C++","checked_on":"2026-10-17","usefulness":"Reference C/C++ runtime for local LLM/VLM inference with GGUF quantization (1.5- to 8-bit), CPU+GPU hybrid offload and many backends (CUDA, HIP, Metal, Vulkan, SYCL, WebGPU). Relevant for local prompt-writing, captioning and VLM agents next to diffusion pipelines.","source_type":"repository","category_ids":["T09"],"dependencies":["backend-specific toolchains (CUDA, Metal, Vulkan, etc.)"],"canonical_url":"https://github.com/ggml-org/llama.cpp","review_status":"reviewed","schema_version":"0.1","execution_status":"not_run","inspection_status":"metadata_checked","upstream_updated_at":"2026-10-17T02:06:45Z","proposed_next_action":"inspect"},"collector":{"file":"research-results/_inbox/lane-b/T09.json","lane":"lane-b","branch":"worktree-agent-a0ed9eed8c015f4b7","commit":"5179ec9","collector":"Claude Sonnet 5.5 (high), combined lane B (T05-T09), founder-run","file_sha256":"2be2976c6cfa49f25020424c09725cd5b5e87725cbf9e577fc2fee2e9610f7b5","merged_from":[],"original_id":"ggml-org--llama.cpp","review_reason":"L07 review 2026-10-17: lane lane-b accepted after automated metadata re-check and sample verification; see review-log.jsonl.","review_status":"reviewed","automated_flags":[]},"observed_on":"2026-10-17","original_id":"ggml-org--llama.cpp","source_file":"content/seeds/research/curated/resources.jsonl","research_side":{"review_status":"reviewed","source_language":"C++","execution_status":"not_run","inspection_status":"metadata_checked","proposed_next_action":"inspect"},"source_schema":"resource-candidate/0.1","original_sha256":"c7abf2d894b10354919507eb3bd934f8331de9765c9d3121cf65858e471a6d8b","unmapped_fields":["language","proposed_next_action"]}],"publication":{"rule":"owner_import_table","policy":"l05-publication/1","visibility":"public"},"research_review":{"by":"research pipeline","as_of":"2026-10-17","status":"reviewed"}}},"parent_id":null,"project_id":null,"reply_count":0,"url":"https://veyrul.com/sources/src_01M569CQZ2C8JW7T207PW1KE1G","api_url":"https://veyrul.com/v1/records/src_01M569CQZ2C8JW7T207PW1KE1G","created_at":"2026-10-18T01:18:05.782Z","updated_at":"2026-10-18T01:18:05.782Z","last_activity_at":"2026-10-18T01:18:05.782Z"}