issues
search
jy-yuan
/
KIVI
KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache
https://arxiv.org/abs/2402.02750
MIT License
120
stars
10
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
An error occurred while using "evaluate. load (" act_match ")"
#12
Felixvillas
opened
6 days ago
1
Which file I need to run to obtain the result in Figure 4?
#11
Felixvillas
opened
1 week ago
2
not support evaluation with ROCM
#10
ym-guan
opened
1 week ago
1
Spport for ChatGLM3
#9
redscv
opened
2 weeks ago
1
Provide an accuracy testing interface?
#8
ascendpoet
closed
5 days ago
1
Discrepancy in Reproduced Results for LLaMA2 on "qmsum" and "qasper" tasks.
#7
ilur98
closed
2 weeks ago
2
W/ or w/o Weight quantization?
#6
deephanson94
closed
5 days ago
4
[fix] add the missing comma in pyproject.toml to enable correct pip i…
#5
wln20
closed
1 month ago
1
Integrate KIVI into inference frameworks?
#4
darrenglow
closed
4 days ago
1
LlamaConfig.attention_dropout does not exist in transformers==4.35.2
#3
RalphMao
closed
1 month ago
1
Could you please open-source the code for the calculation and visualization of the statistic information of KV Cache?
#2
wln20
closed
1 month ago
3
Can this be used with any autogressive model?
#1
hello-fri-end
closed
2 weeks ago
1