Jonathan Borenstein

What an agent can do with the llm-compressor corpus

vllm-project/llm-compressor: State-of-the-art LLM compression, built for production inference with vLLM

• Look up how llm-compressor implements compression, quantization, with answers cited to file and line.
• Reuse a worked example: the commit “Refactor basic calibration to use the sequential pipeline” (4 files · Python).
• Answer from llm-compressor's real Python source instead of memory (AI, prompts and agents).

• Where does llm-compressor handle “Refactor basic calibration to use the sequential pipeline”?
• How does llm-compressor implement compression?
• What does tests do in llm-compressor?

Search the GitHub repository vllm-project/llm-compressor with XERJ (https://hub.xerj.org/corpus/vllm-project--llm-compressor).
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/vllm-project/llm-compressor llm-compressor && git -C llm-compressor checkout 269a4518241db8af3fd4e19c717abf713a176a72
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./llm-compressor --url http://127.0.0.1:9200 --prefix llm-compressor --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: Apache-2.0. Keep the copyright notice and credit the authors.

corpus vllm-project--llm-compressor · AI, prompts and agents
Related corpora: fastrag, btrblocks, headroomlabs-ai/headroom, pranavkumaarofficial/nlcli-wizard
AI search and retrieval with XERJ · Case study: reference coding for agents