Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Log In
Sign Up
Kernels:
kernels-community
/
paged-attention
like
0
Follow
kernels-community
346
Kernel card
Files
Files and versions
xet
Community
attention
Performance
attention
Paged attention kernels from
vLLM
and
mistral.rs
.
Performance
Use this kernel
Downloads last month
-
kernels
apache-2.0
Supported hardwares
new
CUDA
7.5
8.0
8.6
9.0
10.0
B200
192GB
H200
141GB
H100
80GB
L40s
48GB
L40
48GB
L20
48GB
L4
24GB
RTX 6000 Ada
48GB
RTX 5880 Ada
48GB
RTX 5000 Ada
32GB
RTX 4500 Ada
24GB
RTX 4000 Ada
20GB
RTX 4000 SFF Ada
20GB
RTX 2000 Ada
16GB
RTX A6000
48GB
RTX A5000
8GB
RTX A5000 Max-Q
16GB
RTX A5000 Mobile
16GB
RTX A4000
16GB
RTX A4000 Max-Q
8GB
RTX A4000 Mobile
8GB
RTX A3000 Mobile
6GB
RTX A2000
6GB
RTX A2000 Embedded
4GB
RTX A2000 Max-Q
4GB
RTX A2000 Mobile
4GB
A100
80GB
A40
48GB
A30
24GB
A10
24GB
A2
16GB
RTX 4090
24GB
RTX 4090D
24GB
RTX 4090 Mobile
16GB
RTX 4080 SUPER
16GB
RTX 4080
16GB
RTX 4080 Mobile
12GB
RTX 4070
12GB
RTX 4070 Mobile
8GB
RTX 4070 Ti
12GB
RTX 4070 Super
12GB
RTX 4070 Ti Super
16GB
RTX 4060
8GB
RTX 4060 Ti
8GB
RTX 4090 Laptop
16GB
RTX 4080 Laptop
12GB
RTX 4070 Laptop
8GB
RTX 4060 Laptop
8GB
RTX 4050 Laptop
6GB
RTX 3090
24GB
RTX 3090 Ti
24GB
RTX 3080
12GB
RTX 3080 Ti
12GB
RTX 3080 Mobile
8GB
RTX 3070
8GB
RTX 3070 Ti
8GB
RTX 3070 Ti Mobile
8GB
RTX 3060 Ti
8GB
RTX 3060
12GB
RTX 2080 Ti
11GB
RTX 2080
8GB
RTX 2070
8GB
RTX 2070 SUPER Mobile
8GB
RTX 2070 SUPER
8GB
RTX 3060 Mobile
6GB
RTX 3050 Mobile
4GB
RTX 2060
6GB
RTX 2060 12GB
12GB
RTX 2060 Mobile
6GB
RTX Titan
24GB
GTX 1660
6GB
GTX 1650 Mobile
4GB
T4
16GB
T10
16GB
Jetson AGX Orin 64GB
64GB
Jetson AGX Orin 32GB
32GB
Jetson Orin NX 16GB
16GB
Jetson Orin NX 8GB
8GB
Jetson Orin Nano 8GB
8GB
Jetson Orin Nano 4GB
4GB
ROCm
MI300
192GB
MI250
128GB
MI210
64GB
MI100
32GB
MI60
32GB
MI50
16GB
RX 7900 XTX
24GB
RX 7900 XT
20GB
RX 7900 GRE
16GB
RX 7800 XT
16GB
RX 7700 XT
12GB
RX 6950 XT
16GB
RX 6800
16GB
Radeon Pro VII
16GB
Torch
2.10
OS
macos
linux
Arch
x86_64
aarch64