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
4.27k
stars
228
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Output for High Token Languages like Japanese
#63
choprahetarth
opened
6 months ago
2
Fix (LLMLingua): fix the link of llama_index
#62
wlsdml1114
closed
6 months ago
2
Understanding the interplay between `ratio` and `iterative_size`
#61
acnagle
closed
5 months ago
4
Failed Compression Attempts with LLMLingua Web UI Demo
#60
cws322
opened
6 months ago
1
Fix(LLMLingua): fix the force context ids and condition flag
#59
iofu728
closed
6 months ago
1
force_context_ids parameter not behaving as expected
#58
Dakraid
closed
6 months ago
1
Feature(LLMLingua): add alt-gpt reference
#56
iofu728
closed
6 months ago
0
AssertionError: Torch not compiled with CUDA enabled
#55
JiHa-Kim
opened
6 months ago
7
Fix (LLMLingua): Resolved a potential ZeroDivisionError caused by the actual compression ratio.
#54
davidberenstein1957
closed
6 months ago
0
[BUG] ratio computation results in `ZeroDivisionError: division by zero` with `compressed_tokens=0`
#53
davidberenstein1957
closed
6 months ago
1
[design] Interface Design
#52
mydmdm
opened
6 months ago
0
version 0.2.0 iteration plan
#51
mydmdm
closed
4 months ago
1
prompt中的结构化数据
#50
growmuye
opened
6 months ago
2
Some questions about parameters?
#49
XiaoFengbing
opened
6 months ago
5
PromptCompressor error - OpenAIGPTLMHeadModel.forward() got an unexpected keyword argument 'past_key_values'
#48
manojsharmadcx
opened
6 months ago
3
How to setup LLMLingua with localhost?
#47
JiHa-Kim
opened
6 months ago
6
keyError 'llama' when trying to running PromptCompressor()
#46
radcon00
opened
6 months ago
3
compress_prompt Reports Error: AttributeError: 'NoneType' object has no attribute 'device'
#45
xxSpencer
opened
6 months ago
1
Using web-hosted model for inference
#44
dnnp2011
opened
6 months ago
13
The script for LongChat to reproduce the LongLLMLingua
#43
zhyunlong
opened
6 months ago
1
Feature(LLMLingua): add slide of AI Time.
#42
iofu728
closed
6 months ago
0
Support for llama.cpp or exl2
#41
TechnotechGit
opened
6 months ago
5
use other quant formats
#40
zba
opened
6 months ago
1
No improvemence when apply LongLLMLingua after retrieval.
#39
ZhexuanZhou
closed
6 months ago
4
Remove Duplicate Declaration of Loss Function
#38
Speuce
closed
6 months ago
1
сhanged concatenation of strings to f-strings to improve readability
#37
eukub
closed
5 months ago
0
RuntimeError: The expanded size of the tensor (181) must match the existing size (211) at non-singleton dimension 0
#36
kofuya
opened
7 months ago
1
Getting 'Found no NVIDIA driver on your system ' error.
#35
defatoraj
closed
6 months ago
2
llama_index and LLMLingua PromptCompressor inconsistency
#34
argenisleon
closed
7 months ago
1
Prerelease(LLMLingua): fix the license
#32
iofu728
closed
7 months ago
0
how can i use it in langchain?
#31
whm233
closed
4 months ago
2
Fix(LLMLingua): fix typo in DOCUMENT.md
#30
eltociear
closed
7 months ago
0
Codes IPTV
#29
XYJ999
opened
7 months ago
1
autogen compressible agent integration
#28
yenif
opened
7 months ago
1
Fix (LLMLingua): support mps, fix keep_flag out of dimension.
#27
iofu728
closed
7 months ago
0
Update README.md
#26
bobchao
closed
7 months ago
0
Some problem about code
#25
hhy150
closed
7 months ago
2
docs: Autogenerate documentation with Undoc.ai
#24
aidoofus
closed
7 months ago
2
Exploring the Possibility of Porting LLMLingua to JVM Languages (Java/Kotlin)
#23
fabriciorissetto
closed
8 months ago
2
The specific parameter settings in the compressor for reproduce NQ
#22
ignorejjj
opened
8 months ago
4
Feature (LLMLingua): support GPT-Q
#20
iofu728
closed
8 months ago
0
Question about past_key_values
#18
mirth
closed
8 months ago
1
Which version of openai should be installed to reproduce gsm8k with llmlingua?
#17
LYH-YF
opened
8 months ago
3
Fixed(LLMLingua): fix the prefix dimension mismatch.
#16
iofu728
closed
8 months ago
0
Fixed (LLMLingua): Resolved the issue where the context was coming up as empty
#15
iofu728
closed
8 months ago
1
"IndexError: list index out of range" when compressing prompt
#14
elanger4
closed
8 months ago
2
Feature(LongLLMLingua): support reranker model
#13
iofu728
closed
8 months ago
0
Is the code for LongLLMLingua out?
#12
darinkishore
closed
8 months ago
3
Feature(LLMLingua): add examples
#11
iofu728
closed
8 months ago
1
Fix(LLMLingua): typo in README.md
#10
eltociear
closed
8 months ago
1
Previous
Next