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
4.42k
stars
241
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Fixed(LLMLingua): fix the prefix dimension mismatch.
#16
iofu728
closed
9 months ago
0
Fixed (LLMLingua): Resolved the issue where the context was coming up as empty
#15
iofu728
closed
9 months ago
1
"IndexError: list index out of range" when compressing prompt
#14
elanger4
closed
9 months ago
2
Feature(LongLLMLingua): support reranker model
#13
iofu728
closed
10 months ago
0
Is the code for LongLLMLingua out?
#12
darinkishore
closed
10 months ago
3
Feature(LLMLingua): add examples
#11
iofu728
closed
10 months ago
1
Fix(LLMLingua): typo in README.md
#10
eltociear
closed
10 months ago
1
Feature(LLMLingua): update the news
#9
iofu728
closed
10 months ago
0
Out of Memory Error with Llama-2-7b
#8
ankitpdc
closed
10 months ago
3
What the setting of parameters needed to reproduce the LongLLMLingua?
#7
czwlines
closed
10 months ago
1
Out of Memory error with llm_lingua
#6
ankitpdc
closed
10 months ago
3
Can you provide the NaturalQuestions test dataset?
#5
czwlines
closed
10 months ago
2
When I use chinese llama, the compressed prompt has garbled code
#4
seanzhang-zhichen
opened
11 months ago
9
How about compress a whole book?
#3
lucasjinreal
opened
11 months ago
5
Feature(LLMLingua): release LLMLingua code & demo
#2
iofu728
closed
11 months ago
1
Action required: migrate or opt-out of migration to GitHub inside Microsoft
#1
microsoft-github-policy-service[bot]
closed
1 year ago
2
Previous