kvpress
Efficiently compress the KV cache of any pretrained transformer
- Latest release
- Apr 09, 2026
- Releases
- 26
- Known CVEs
- 0
- First release
- Nov 13, 2024
- License
- —
Insights
Activity
- Total releases
- 26
- Last 12 months
- 13
- Cadence
- ~9 days
- Dependencies
- 17
Releases per month
last 12 monthsRelease mix
- minor 5
- patch 20
26
releases
Dependencies
Depends on
0.5.3-
accelerate <2,>=1.0.0
-
bert-score <0.4,>=0.3.13
-
cachetools <6,>=5.5.2
-
datasets >=2.21.0
-
fire <0.7,>=0.6.0
-
flash-attn
-
fuzzywuzzy >=0.18.0
-
jieba >=0.42.1
-
nltk <4,>=3.9.1
-
numpy <3,>=2.0.0
1–10 of 17
Used by
2Releases
| Version | Released | |
|---|---|---|
0.5.3
patch
|
0.5.3
patch
Dependencies (17)
+ 9 more |
|
0.5.2
patch
|
0.5.2
patch
|
|
0.5.1
patch
|
0.5.1
patch
|
|
0.5.0
minor
|
0.5.0
minor
|
|
0.4.3
patch
|
0.4.3
patch
|
|
0.4.2
patch
|
0.4.2
patch
|
|
0.4.1
patch
|
0.4.1
patch
|
|
0.4.0
minor
|
0.4.0
minor
|
|
0.3.0
minor
|
0.3.0
minor
|
|
0.2.10
patch
|
0.2.10
patch
|
|
0.2.9
patch
|
0.2.9
patch
|
|
0.2.8
patch
|
0.2.8
patch
|
|
0.2.7
patch
|
0.2.7
patch
|
|
0.2.6
patch
|
0.2.6
patch
|
|
0.2.5
patch
|
0.2.5
patch
|
|
0.2.4
patch
|
0.2.4
patch
|
|
0.2.3
patch
|
0.2.3
patch
|
|
0.2.2
patch
|
0.2.2
patch
|
|
0.2.1
patch
|
0.2.1
patch
|
|
0.2.0
minor
|
0.2.0
minor
|
1–20 of 26