{
 "schema_version": 1,
 "generated": "2026-10-20",
 "id": "jakeatx-llamampere--reuse-prebuilt-cache-for-repeat-evals",
 "repo": "JakeATX/llamAmpere",
 "repo_url": "https://github.com/JakeATX/llamAmpere",
 "repo_slug": "jakeatx-llamampere",
 "title": "Speed up repeat evals with a prebuilt prompt cache",
 "page_title": "How to speed up repeat evals with a prebuilt prompt cache with Llam Ampere",
 "summary": "Point llama-server at a read-only prompt cache folder so long eval prompts skip re-reading.",
 "who": "An ML engineer or researcher who runs the same long eval or benchmark prompts many times against Swift 1.5 on Llam Ampere.",
 "problem": "Each eval run re-reads the same long prompts, which wastes time on every repeat run.",
 "outcome": "Eval prompts load from a prebuilt folder, and at temperature 0 the output matches the uncached run according to the README.",
 "steps": [
  "Complete the build in the first use case so `./build-sm86/bin/llama-server` exists in the Llam Ampere folder.",
  "Download a ready-made cache folder from https://huggingface.co/datasets/jakeatx/llamampere-evalcache to a local directory. (inferred, check the README)",
  "Start the server with the Swift 1.5 command from the 24 GB use case and add `--eval-cache <cache directory>`. (inferred, check the README)",
  "Run the same eval prompts twice at temperature 0 and compare the outputs and the timing.",
  "Check the server log to confirm that the eval prompts loaded from the cache folder."
 ],
 "agent_prompt": "In the llamAmpere repo at <repo path>, start llama-server with the Swift 1.5 model and `--eval-cache <cache directory>`. Run the eval prompts in <eval file> twice at temperature 0 and report the time of each run and whether the two outputs match. Verify that the second run is faster and that the outputs are identical.",
 "agents": [
  "any"
 ],
 "difficulty": "Advanced",
 "time": "1.5 hours",
 "basis": "readme",
 "caveat": "The README describes --eval-cache as an opt-in, read-only cache for eval and benchmark prompts, and it does not give the exact command syntax, so check the release notes at docs/llamampere-v0.5.5/RELEASE_NOTES.md before running it.",
 "category": "Software and DevOps",
 "tags": [
  "Software and DevOps"
 ],
 "lang": "c++",
 "requirements": [
  "Linux machine with an NVIDIA card (RTX 3090 or 3090 Ti with 24 GB for the main path, or a 12 GB card for the low-memory path)",
  "CUDA toolkit (the README tested with 12.4), CMake, git and a C++ compiler",
  "Disk space and network access for the model download: 15.6 GB for the 24 GB path, 9.0 GB for the 12 GB path",
  "Recommended: OpenSSL development files are not needed if you use the -DLLAMA_BUILD_BORINGSSL=ON build flag, which lets -hf download the model"
 ],
 "risk": "dual-use",
 "seen_in_the_wild": false,
 "mentioned_publicly": false,
 "risks": [],
 "best": false,
 "score": 0.8,
 "evidence": [],
 "url": "https://dedupedai.com/use-cases/jakeatx-llamampere/reuse-prebuilt-cache-for-repeat-evals/",
 "md": "https://dedupedai.com/use-cases/jakeatx-llamampere/reuse-prebuilt-cache-for-repeat-evals/index.md",
 "disclaimer": "Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked \"Seen in the wild\", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email hello@dedupedai.com and we will look at it promptly.",
 "api": "https://dedupedai.com/api/v1/usecases/jakeatx-llamampere--reuse-prebuilt-cache-for-repeat-evals.json",
 "api_version": "v1"
}