| { |
| "_comment": [ |
| "Pinned llama.cpp builds, fetched and verified by distinct_agent/runtime.py.", |
| "A worker downloads the build recorded here and refuses to install it unless", |
| "the bytes hash to `sha256`.", |
| "", |
| "KEYS. `windows-x64` is the build that runs on any Windows x64 machine, and", |
| "is the fallback every machine can reach. A key with a suffix is an", |
| "accelerated build offered only to a machine that has been checked for the", |
| "hardware: `windows-x64-cuda` needs an NVIDIA driver advertising at least", |
| "`requires_cuda`, which the worker reads from NVML. If it will not start,", |
| "the worker steps down to the plain key rather than leaving a volunteer", |
| "with a worker that does not boot.", |
| "", |
| "ARCHIVES. An accelerated build is not self-contained: llama.cpp ships the", |
| "CUDA binaries in one archive and the CUDA runtime libraries they link", |
| "against in another. Both are listed, both are verified, and either both", |
| "install or neither does.", |
| "", |
| "A platform with no entry gets no automatic download. That is deliberate:", |
| "this project already withholds a MODEL whose digest it cannot check, and", |
| "the program that executes those models is held to the same bar. Operators", |
| "on those platforms pass --llama-server, or run --demo-runner and offer the", |
| "library's tools and skills with no model at all.", |
| "", |
| "TO ADD OR MOVE A PIN: download the asset, hash it, and record the result", |
| "here. `scripts/record_llama_pin.py` does exactly that and prints the JSON;", |
| "`scripts/apply_llama_pin.py` merges what it printed into this file. Never", |
| "copy a digest from a release page or an API response: a digest that arrived", |
| "with the download proves only that the bytes were not corrupted in transit,", |
| "which TLS already said, and pinning it would dress trust-on-first-use up as", |
| "verification." |
| ], |
| "builds": { |
| "windows-x64": { |
| "tag": "b10742", |
| "accelerator": "cpu", |
| "archives": [ |
| { |
| "asset": "llama-b10742-bin-win-cpu-x64.zip", |
| "url": "https://github.com/ggml-org/llama.cpp/releases/download/b10742/llama-b10742-bin-win-cpu-x64.zip", |
| "sha256": "a923d80953d618335ae0073233fdcfb93760dfde646e957786894259aba87d72", |
| "bytes": 18373032 |
| } |
| ] |
| }, |
| "windows-x64-cuda": { |
| "tag": "b10742", |
| "accelerator": "cuda", |
| "requires_cuda": 12040, |
| "archives": [ |
| { |
| "asset": "llama-b10742-bin-win-cuda-12.4-x64.zip", |
| "url": "https://github.com/ggml-org/llama.cpp/releases/download/b10742/llama-b10742-bin-win-cuda-12.4-x64.zip", |
| "sha256": "2249c7e6337ea02a7f0c0832a2826e5a6de28b87f216427e746e50e86b87bba4", |
| "bytes": 254220199 |
| }, |
| { |
| "asset": "cudart-llama-bin-win-cuda-12.4-x64.zip", |
| "url": "https://github.com/ggml-org/llama.cpp/releases/download/b10742/cudart-llama-bin-win-cuda-12.4-x64.zip", |
| "sha256": "8c79a9b226de4b3cacfd1f83d24f962d0773be79f1e7b75c6af4ded7e32ae1d6", |
| "bytes": 391443627 |
| } |
| ] |
| } |
| } |
| } |
|
|
