Lowaltitudeflight

What an agent can do with the local-llm-tuning-guide corpus

Lowaltitudeflight/local-llm-tuning-guide: A decision library for running local LLMs on multi-GPU machines without NVLink: parallelism, communication, quantization, speculative…

• Look up how local-llm-tuning-guide implements benchmarking, decision-guide, gpu-serving, with answers cited to file and line.
• Reuse a worked example: the commit “MiniMax-M3.1-Flash SM120 data, 4x72 recipe, model matrix, topol…” (15 files · Python).
• Answer from local-llm-tuning-guide's real Python source instead of memory (AI, prompts and agents).

• How does local-llm-tuning-guide implement benchmarking?
• What does tools do in local-llm-tuning-guide?

Search the GitHub repository Lowaltitudeflight/local-llm-tuning-guide with XERJ (https://hub.xerj.org/corpus/lowaltitudeflight--local-llm-tuning-guide).
Run these in a shell, in order, and check each result before the next:
1. xerj --help  (success: it prints usage). If xerj is missing: curl -fsSL https://xerj.org/get | sh
2. git clone https://github.com/Lowaltitudeflight/local-llm-tuning-guide local-llm-tuning-guide && git -C local-llm-tuning-guide checkout 23cb9c3a7ef5e6cfa9c90f6cc1d03a585349cf00
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./local-llm-tuning-guide --url http://127.0.0.1:9200 --prefix local-llm-tuning-guide --progress plain
5. xerj autoindex map --url http://127.0.0.1:9200
Then answer my question from the indexed files and cite the ax_path of every hit. Query syntax: https://xerj.org/llms.txt
Licence: MIT. Keep the copyright notice and credit the authors.

corpus lowaltitudeflight--local-llm-tuning-guide · AI, prompts and agents
Related corpora: ann-benchmarks, cognita, tanveer-arch/promptdrift, SoheilGtex/finance-data-pipelines
AI search and retrieval with XERJ · Case study: reference coding for agents