llmlingua

pypiv0.2.2

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.

License MIT Licensepermissive14 versions1 maintainers24 deps14,978 weekly dl
microsoft/LLMLingua
46
/ 100
Health
safe to use

[email protected] is safe to use (health: 46/100)

Health breakdown0 – 100
0/25
maintenance
10/20
popularity
25/25
security
9/15
maturity
2/15
community
Vulnerabilities
0
none known

Health History

Dependency Tree

License Audit

Dependencies (24)
transformersacceleratetorchtiktokennltknumpytransformersaccelerate;torch;tiktoken;nltk;numpy;blackflake8isortpre-commit;pytest;pytest-xdist;blackflake8isortpre-commit;pytest;pytest-xdist;
API access

Get this data programmatically — free, no authentication.

curl https://depscope.dev/api/check/pypi/llmlingua
More from pypi
requestscharset_normalizeraiobotocoreclicknumpypycparser
Browse all pypi packages →

Last updated · 2024-04-09T08:21:55.428185Z