Skip to content

need help failed to run demo3 with L40s GPU installed well #11

@gaowayne

Description

@gaowayne

hello guys, follow the intruction to run cache blend demo. then I suffer below error

anyone can shed some light?

root@salab-hpedl380g11-03:~/wayne/kvcache/demo# ls
demo1-quickstart  demo2-multi-node-sharing  demo3-KV-blending  demo4-compare-with-vllm  LICENSE  README.md
root@salab-hpedl380g11-03:~/wayne/kvcache/demo# cd demo3-KV-blending/
root@salab-hpedl380g11-03:~/wayne/kvcache/demo/demo3-KV-blending# ls
chat_session.py  data  frontend.py  README.md  run-server.sh.template  stop-dockers.sh
root@salab-hpedl380g11-03:~/wayne/kvcache/demo/demo3-KV-blending# cp run-server.sh.template run-server.sh
root@salab-hpedl380g11-03:~/wayne/kvcache/demo/demo3-KV-blending# vim run-server.sh
root@salab-hpedl380g11-03:~/wayne/kvcache/demo/demo3-KV-blending# bash ./run-server.sh
lmcache-blend: Pulling from apostacyh/vllm
aece8493d397: Pull complete 
45f7ea5367fe: Pull complete 
3d97a47c3c73: Pull complete 
12cd4d19752f: Pull complete 
da5a484f9d74: Pull complete 
05e7384ae9b3: Pull complete 
b8ae4c36c787: Pull complete 
5d2454ae34bc: Pull complete 
c22dc14fb058: Pull complete 
089112ee8c16: Pull complete 
849af6542ef4: Pull complete 
65d56448b8e1: Pull complete 
4f4fb700ef54: Pull complete 
ff72ecef08d2: Pull complete 
43315d1d9bdd: Pull complete 
d3145db057a2: Pull complete 
21feca74d50f: Pull complete 
d9b0f72b4d31: Pull complete 
6e541d84b188: Pull complete 
7fbf8ab87f94: Pull complete 
2c3bd89084bb: Pull complete 
2dccf2e467bf: Pull complete 
Digest: sha256:98bb3846125f5bd505f4c61742df9ef6d65100f50fb7b21a781aef16739818fa
Status: Downloaded newer image for apostacyh/vllm:lmcache-blend
docker.io/apostacyh/vllm:lmcache-blend
docker: Error response from daemon: could not select device driver "" with capabilities: [[gpu]]

Run 'docker run --help' for more information
root@salab-hpedl380g11-03:~/wayne/kvcache/demo/demo3-KV-blending# 
root@salab-hpedl380g11-03:~# nvidia-smi
Fri Apr 25 08:24:34 2025       
+-----------------------------------------------------------------------------------------+
| NVIDIA-SMI 550.144.03             Driver Version: 550.144.03     CUDA Version: 12.4     |
|-----------------------------------------+------------------------+----------------------+
| GPU  Name                 Persistence-M | Bus-Id          Disp.A | Volatile Uncorr. ECC |
| Fan  Temp   Perf          Pwr:Usage/Cap |           Memory-Usage | GPU-Util  Compute M. |
|                                         |                        |               MIG M. |
|=========================================+========================+======================|
|   0  NVIDIA L40S                    Off |   00000000:8A:00.0 Off |                    0 |
| N/A   36C    P8             24W /  350W |       1MiB /  46068MiB |      0%      Default |
|                                         |                        |                  N/A |
+-----------------------------------------+------------------------+----------------------+
                                                                                         
+-----------------------------------------------------------------------------------------+
| Processes:                                                                              |
|  GPU   GI   CI        PID   Type   Process name                              GPU Memory |
|        ID   ID                                                               Usage      |
|=========================================================================================|
|  No running processes found                                                             |
+-----------------------------------------------------------------------------------------+

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions