AI 工具AI TOOLS· MODEL-INFRA
microsoft/LLMLingua
压缩提示文本,让大模型跑得更快、更省钱,还不怎么掉效果。Compresses long prompts so LLMs run faster and cheaper without losing the key points.
根据公开文档整理,未运行实测;费用以项目官网为准。Based on public documentation, without runtime testing. Check the project site for pricing.
能力CAPABILITIES
压缩提示,节省 接口 费用
加快AI 模型的回答速度
保留关键信息,不影响回答质量
按段落控制压缩程度
Compress prompts to a fraction of their original size.
Keep instructions and questions intact while shrinking context.
Tune the compression ratio to meet a token budget.
Reorder and filter context for long conversations.
Reduce jailbreak risk with a security-aware mode.
上手GET STARTED
pip install llmlingua选择与你的环境对应的方式。命令来自项目文档,未运行实测。Choose the option for your environment. Commands come from project documentation and have not been run-tested.
使用限制LIMITATIONS
以下要求与风险来自文档静态检查,未执行项目代码;扫描没有命中,不代表使用安全。Risk here is evidence, not an alarm. These findings come from static scanning of the docs; we never execute a project’s code.
限制LIMITS
未知Unknown
静态扫描STATIC SCAN
在 README、SKILL.md 和依赖清单中没有匹配到已知风险模式。No known risk patterns matched in the README, SKILL.md or dependency list.
静态扫描未发现明显风险,但不代表安全。仅核验官方页面,未审计服务端代码;数据处理和费用以官网为准。The static scan of the documentation found no known risk patterns, but that does not prove the project is safe.
项目动态PROJECT ACTIVITY
首次发现FIRST SEEN
03 OCT 202603 OCT 2026
增长GROWTH
+1.8%+1.8%
6.7k → 6.8k stars · 50 个快照6.7k → 6.8k stars · 50 snapshots
讨论DISCUSSION
1 SOURCES1 SOURCES
2 条外部提及2 external mentions
状态STATUS
持续活跃Active
质量 AQuality A
最高20倍压缩,大幅降低LLM API的token消耗和成本Published at EMNLP 2023 and ACL 2024
HN_STORY · 149 points · 47 comments
HN_STORY · 1 points · 0 comments
{
"agents": [
{
"agent": "opencode",
"evidence": "readme: …deofconduct/faq/) or contact [opencode@microsoft.com](mailto:opencod…"
}
],
"apiKey": null,
"docker": null,
"taxonomy": {
"scores": {
"design": 0,
"ai-tools": 6,
"dev-tools": 0,
"indie-web": 0,
"skill-agent": 0,
"productivity": 2
},
"primary": "ai-tools",
"secondary": "model-infra"
},
"localRuntime": "-7b-Chat-GPTQ, only need <8GB GPU memory. ## Before that, you need to pip",
"skillMdTotal": 0,
"skillMdErrors": [],
"treeTruncated": false,
"categoryScores": {
"data": 3,
"agent": 0,
"media": 0,
"design": 0,
"browser": 0,
"devtool": 0,
"security": 0,
"marketing": 0,
"productivity": 1
},
"classification": [
{
"signal": "description mentions AI",
"weight": 0.2
}
],
"scannedSources": [
"readme"
],
"skillMdFetched": 0
}