{"package": "llmlingua-promptflow", "summary": "To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.", "pypi_url": "https://pypi.org/project/llmlingua-promptflow", "piwheels_url": "https://www.piwheels.org/project/llmlingua-promptflow", "releases": {"0.0.1": {"released": "2024-05-08 06:38:19", "prerelease": false, "yanked": false, "skip_reason": "", "files": {"llmlingua_promptflow-0.0.1-py3-none-any.whl": {"file_url": "https://archive1.piwheels.org/simple/llmlingua-promptflow/llmlingua_promptflow-0.0.1-py3-none-any.whl", "filehash": "dc39420125d843306fad889c5804cf78fa5a897d51bb5c1ad8916244a109d234", "filesize": 18833, "builder_abi": "cp311", "file_abi_tag": "none", "platform": "any", "requires_python": ">=3.8.0", "apt_dependencies": [], "pip_dependencies": ["nltk", "numpy", "tiktoken", "transformers"]}}}}}