vastai update workergroup

Update an existing autoscale group

Usage

vastai update workergroup WORKERGROUP_ID --endpoint_id ENDPOINT_ID [options]

Arguments

id · integer · required

id of autoscale group to update

Options

--min_load · number

minimum floor load in perf units/s (token/s for LLms)

--target_util · number

target capacity utilization (fraction, max 1.0, default 0.9)

--cold_mult · number

cold/stopped instance capacity target as multiple of hot capacity target (default 2.5)

--cold_workers · integer

min number of workers to keep ‘cold’ for this workergroup

--test_workers · integer

number of workers to create to get an performance estimate for while initializing workergroup (default 3)

--gpu_ram · number

estimated GPU RAM req (independent of search string)

--template_hash · string

template hash (Note: if you use this field, you can skip search_params, as they are automatically inferred from the template)

--template_id · integer

template id

--search_params · string

search param string for search offers ex: “gpu_ram>=23 num_gpus=2 gpu_name=RTX_4090 inet_down>200 direct_port_count>2 disk_space>=64”

-n · boolean

Disable default search param query args (alias: --no-default)

--launch_args · string

launch args string for create instance ex: “—onstart onstart_wget.sh —env ‘-e ONSTART_PATH=https://s3.amazonaws.com/public.vast.ai/onstart_OOBA.sh’ —image atinoda/text-generation-webui:default-nightly —disk 64”

--endpoint_name · string

deployment endpoint name (allows multiple workergroups to share same deployment endpoint)

--endpoint_id · integer

deployment endpoint id (allows multiple workergroups to share same deployment endpoint)

Description

Example: vastai update workergroup 4242 —min_load 100 —target_util 0.9 —cold_mult 2.0 —search_params “gpu_ram>=23 num_gpus=2 gpu_name=RTX_4090 inet_down>200 direct_port_count>2 disk_space>=64” —launch_args “—onstart onstart_wget.sh —env ‘-e ONSTART_PATH=https://s3.amazonaws.com/public.vast.ai/onstart_OOBA.sh’ —image atinoda/text-generation-webui:default-nightly —disk 64” —gpu_ram 32.0 —endpoint_name “LLama” —endpoint_id 2

Global Options

The following options are available for all commands:

Option	Description
--url URL	Server REST API URL
--retry N	Retry limit
--raw	Output machine-readable JSON
--explain	Verbose explanation of API calls
--api-key KEY	API key (defaults to ~/.config/vastai/vast_api_key)