forked from akash-network/awesome-akash
-
Notifications
You must be signed in to change notification settings - Fork 0
/
deploy.yaml
64 lines (64 loc) · 2.07 KB
/
deploy.yaml
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
version: "2.0"
services:
text-generation-webui:
# v1.7 of text-generation-webui change this if you want to use a newer/older version
image: zjuuu/text-generation-webui:v1.7.3
expose:
# ui port
- port: 7860
as: 80
to:
- global: true
# api port
- port: 5000
as: 5000
to:
- global: true
# api-stream port
- port: 5005
as: 5005
to:
- global: true
env:
- CLI_ARGS=--listen --auto-devices --api
# the following examples have been tested with the files linked in docs/README_docker.md:
# example running 13b with 4bit/128 groupsize : CLI_ARGS=--model llama-13b-4bit-128g --wbits 4 --listen --groupsize 128 --pre_layer 25
# example with loading api extension and public share: CLI_ARGS=--model llama-7b-4bit --wbits 4 --listen --auto-devices --no-stream --extensions api --share
# example running 7b with 8bit groupsize : CLI_ARGS=--model llama-7b --load-in-8bit --listen --auto-devices
profiles:
compute:
text-generation-webui:
resources:
cpu:
units: 6
memory:
size: 16Gi
gpu:
units: 1
attributes:
vendor:
nvidia:
# some models require a lot of vram to run please research the requirements of the model you want to deploy and use a capable gpu
# uncomment or leave it empty to receive bids with any available gpu
#- model: rtx4090
#- model: rtx3090
#- model: rtx3090
#- model: h100
#- model: a100
#- model: v100
#- model: rtx3060ti
#- model: p100
# Size of the storage depends on the models you want to download
storage:
- size: 30Gi
placement:
westcoast:
pricing:
text-generation-webui:
denom: uakt
amount: 1000000
deployment:
text-generation-webui:
westcoast:
profile: text-generation-webui
count: 1