issues
search
microsoft
/
LLMLingua
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.
https://llmlingua.com/
MIT License
4.18k
stars
222
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
[Question]: LongLLMLingua vs. LLMLingua2 for chatbot history compression
#113
DomStan
closed
3 months ago
1
Feature(LLMLingua-2): update paper link
#112
iofu728
closed
3 months ago
1
Feature(LLMLingua-2): add LLMLingua-2
#111
iofu728
closed
3 months ago
0
version 0.2.1 iteration plan
#110
iofu728
closed
3 months ago
1
Release(LLMLingua): release v0.2.0
#109
iofu728
closed
3 months ago
0
Fix(LLMLingua): fix the release workflow
#108
iofu728
closed
3 months ago
0
Fix(LLMLingua): fix the release workflows
#107
iofu728
closed
3 months ago
0
[Question]: access to public storage https://openaipublic.blob.core.windows.net/ is prohibited in secure environments ,
#106
amrosalehms
opened
4 months ago
3
[Question]: How to only compress documents in the RAG setting?
#105
Hannibal046
closed
3 months ago
1
[Bug]: Compression truncates words and sentences
#104
younes-io
opened
4 months ago
3
[Question]: Incorrect `condition_mode` parameter value in `get_condition_ppl` function
#103
charloco
closed
4 months ago
2
fix sentence-filter adding separator bug and add document
#102
SiyunZhao
closed
3 months ago
0
[Feature Request]: Token compression using GPT-3.5-turbo
#101
ohdearquant
opened
4 months ago
3
[Question]: Running LLMLingua with GGUF models
#100
92dev
opened
4 months ago
1
Feature(LongLLMLingua): update conference
#99
iofu728
closed
4 months ago
0
[Question]: Why set "cache_dir" to "/tmp/cache" on macOS when passing mps as device_map?
#98
danny-su
opened
4 months ago
3
Feature(LLMLingua): add LangChain example
#97
iofu728
closed
4 months ago
0
Feature (LLMLingua): support customized compression spec
#96
iofu728
closed
4 months ago
0
Added unittest for structured_compress_prompt and fixed bugs
#95
SiyunZhao
closed
4 months ago
1
Issues with reproducing LongLLMLingua on the LongBench dataset.
#94
yunlongia
opened
4 months ago
5
Experiments with Alphanumeric Entities
#93
jasonngap1
opened
4 months ago
3
Feature(LLMLingua): add unitest
#92
iofu728
closed
4 months ago
0
change input parameter from ratio to rate
#91
SiyunZhao
closed
4 months ago
0
change parameter from ratio to rate
#90
SiyunZhao
closed
4 months ago
0
Enhancing quality - Recovery settings
#89
synergiator
opened
4 months ago
1
Feature(LLMLingua): update the FAQ
#88
iofu728
closed
4 months ago
0
Hotfix (LLMLingua): fix the out of range
#87
iofu728
closed
4 months ago
1
How to reproduce Multidocument QA results under 9th?
#86
Twilightaaa
opened
4 months ago
5
PromptCompressor -- Missing Package Accelerate but it is installed
#85
shannonlal
closed
4 months ago
1
Index error for small token amounts
#84
oz03-hub
closed
4 months ago
3
Compatible models
#83
oz03-hub
opened
5 months ago
1
error on chatglm3-6b-32k
#82
yuemengrui
closed
4 months ago
1
add structured prompt compress
#81
SiyunZhao
closed
5 months ago
2
Retaining context metadata
#80
thehapyone
closed
4 months ago
2
LLMLingua doesn't work on CPU as device_map
#79
MrTBH
opened
5 months ago
1
Getting errors when running phi2
#78
TempusFugit05
opened
5 months ago
1
LLMLingua and LongLLMLingua parameters question
#76
XiaoFengbing
opened
5 months ago
3
How to run in linux machine (CPU without GPU)
#75
gayuoptisol
opened
5 months ago
2
llama instead of gpt
#74
jwahnn
opened
5 months ago
3
Question about LongLLMLingua token-level compression
#73
eunseongc
closed
5 months ago
2
run local error
#72
songsh
opened
5 months ago
3
Why no integration with Langchain till now?
#71
AIAnytime
closed
4 months ago
8
Curious to integrate together.ai API to optimize the latency.
#70
Pr0fe5s0r
opened
5 months ago
2
Feature (LLMLingua): Add Docstring for PromptCompressor Class
#69
SiyunZhao
closed
5 months ago
0
Params to use for compressing Dialogues
#68
vikram71198
closed
5 months ago
3
Feature(LLMLingua): support phi-2
#67
iofu728
closed
5 months ago
0
CUDA out of memory
#66
deltawi
opened
5 months ago
1
Support for remote LLM through API
#65
deltawi
opened
5 months ago
4
Speed Up Compression
#64
pathquester
opened
5 months ago
6
Output for High Token Languages like Japanese
#63
choprahetarth
opened
5 months ago
2
Previous
Next