mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-08 04:54:38 +00:00
chore!: remove --image-type and --image-name from llama stack run
# What does this PR do? ## Test Plan
This commit is contained in:
Eric Huang
parent
0751002bf3
commit
59b0b71df2
4 changed files with 706 additions and 909 deletions
|
|
@ -322,20 +322,20 @@ Now, let's start the Llama Stack Distribution Server. You will need the YAML con
|
|||
llama stack run -h
|
||||
usage: llama stack run [-h] [--port PORT] [--image-name IMAGE_NAME]
|
||||
[--image-type {venv}] [--enable-ui]
|
||||
[config | template]
|
||||
[config | distro]
|
||||
|
||||
Start the server for a Llama Stack Distribution. You should have already built (or downloaded) and configured the distribution.
|
||||
|
||||
positional arguments:
|
||||
config | template Path to config file to use for the run or name of known template (`llama stack list` for a list). (default: None)
|
||||
config | distro Path to config file to use for the run or name of known distro (`llama stack list` for a list). (default: None)
|
||||
|
||||
options:
|
||||
-h, --help show this help message and exit
|
||||
--port PORT Port to run the server on. It can also be passed via the env var LLAMA_STACK_PORT. (default: 8321)
|
||||
--image-name IMAGE_NAME
|
||||
Name of the image to run. Defaults to the current environment (default: None)
|
||||
[DEPRECATED] This flag is no longer supported. Please activate your virtual environment before running. (default: None)
|
||||
--image-type {venv}
|
||||
Image Type used during the build. This should be venv. (default: None)
|
||||
[DEPRECATED] This flag is no longer supported. Please activate your virtual environment before running. (default: None)
|
||||
--enable-ui Start the UI server (default: False)
|
||||
```
|
||||
|
||||
|
|
@ -347,9 +347,6 @@ llama stack run tgi
|
|||
|
||||
# Start using config file
|
||||
llama stack run ~/.llama/distributions/llamastack-my-local-stack/my-local-stack-run.yaml
|
||||
|
||||
# Start using a venv
|
||||
llama stack run --image-type venv ~/.llama/distributions/llamastack-my-local-stack/my-local-stack-run.yaml
|
||||
```
|
||||
|
||||
```
|
||||
|
|
|
|||
|
|
@ -88,195 +88,8 @@
|
|||
"id": "J2kGed0R5PSf",
|
||||
"outputId": "2478ea60-8d35-48a1-b011-f233831740c5"
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Requirement already satisfied: uv in /opt/homebrew/Caskroom/miniconda/base/envs/l4/lib/python3.10/site-packages (0.6.12)\n",
|
||||
"\u001b[2mUsing Python 3.10.16 environment at: /opt/homebrew/Caskroom/miniconda/base/envs/l4\u001b[0m\n",
|
||||
"\u001b[2mAudited \u001b[1m1 package\u001b[0m \u001b[2min 83ms\u001b[0m\u001b[0m\n",
|
||||
"Environment '/Users/erichuang/projects/internal-llama-stack/.venv' already exists, re-using it.\n",
|
||||
"Virtual environment /Users/erichuang/projects/internal-llama-stack/.venv is already active\n",
|
||||
"\u001b[2mUsing Python 3.11.11 environment at: /Users/erichuang/projects/internal-llama-stack/.venv\u001b[0m\n",
|
||||
"\u001b[2mAudited \u001b[1m1 package\u001b[0m \u001b[2min 387ms\u001b[0m\u001b[0m\n",
|
||||
"Installing pip dependencies\n",
|
||||
"\u001b[2mUsing Python 3.11.11 environment at: /Users/erichuang/projects/internal-llama-stack/.venv\u001b[0m\n",
|
||||
"\u001b[2K\u001b[2mResolved \u001b[1m123 packages\u001b[0m \u001b[2min 1.13s\u001b[0m\u001b[0m \u001b[0m\n",
|
||||
"\u001b[2K\u001b[37m⠙\u001b[0m \u001b[2mPreparing packages...\u001b[0m (0/6) \n",
|
||||
"\u001b[2K\u001b[1A\u001b[37m⠙\u001b[0m \u001b[2mPreparing packages...\u001b[0m (0/6)-----\u001b[0m\u001b[0m 0 B/9.53 KiB \u001b[1A\n",
|
||||
"\u001b[2K\u001b[1A\u001b[37m⠙\u001b[0m \u001b[2mPreparing packages...\u001b[0m (0/6)-\u001b[2m\u001b[0m\u001b[0m 9.53 KiB/9.53 KiB \u001b[1A\n",
|
||||
"\u001b[2mshellingham\u001b[0m \u001b[32m------------------------------\u001b[2m\u001b[0m\u001b[0m 9.53 KiB/9.53 KiB\n",
|
||||
"\u001b[2K\u001b[2A\u001b[37m⠙\u001b[0m \u001b[2mPreparing packages...\u001b[0m (0/6)----\u001b[0m\u001b[0m 0 B/44.00 KiB \u001b[2A\n",
|
||||
"\u001b[2mshellingham\u001b[0m \u001b[32m------------------------------\u001b[2m\u001b[0m\u001b[0m 9.53 KiB/9.53 KiB\n",
|
||||
"\u001b[2K\u001b[2A\u001b[37m⠙\u001b[0m \u001b[2mPreparing packages...\u001b[0m (0/6)----\u001b[0m\u001b[0m 14.88 KiB/44.00 KiB \u001b[2A\n",
|
||||
"\u001b[2mshellingham\u001b[0m \u001b[32m------------------------------\u001b[2m\u001b[0m\u001b[0m 9.53 KiB/9.53 KiB\n",
|
||||
"\u001b[2mtabulate \u001b[0m \u001b[32m\u001b[2m------------------------------\u001b[0m\u001b[0m 0 B/34.43 KiB\n",
|
||||
"\u001b[2K\u001b[3A\u001b[37m⠙\u001b[0m \u001b[2mPreparing packages...\u001b[0m (0/6)----\u001b[0m\u001b[0m 14.88 KiB/44.00 KiB \u001b[3A\n",
|
||||
"\u001b[2mshellingham\u001b[0m \u001b[32m------------------------------\u001b[2m\u001b[0m\u001b[0m 9.53 KiB/9.53 KiB\n",
|
||||
"\u001b[2mtabulate \u001b[0m \u001b[32m-------------\u001b[2m-----------------\u001b[0m\u001b[0m 14.83 KiB/34.43 KiB\n",
|
||||
"\u001b[2K\u001b[3A\u001b[37m⠙\u001b[0m \u001b[2mPreparing packages...\u001b[0m (0/6)----\u001b[0m\u001b[0m 14.88 KiB/44.00 KiB \u001b[3A\n",
|
||||
"\u001b[2meval-type-backport\u001b[0m \u001b[32m\u001b[2m------------------------------\u001b[0m\u001b[0m 0 B/5.69 KiB\n",
|
||||
"\u001b[2mshellingham\u001b[0m \u001b[32m------------------------------\u001b[2m\u001b[0m\u001b[0m 9.53 KiB/9.53 KiB\n",
|
||||
"\u001b[2mtabulate \u001b[0m \u001b[32m-------------\u001b[2m-----------------\u001b[0m\u001b[0m 14.83 KiB/34.43 KiB\n",
|
||||
"\u001b[2K\u001b[4A\u001b[37m⠙\u001b[0m \u001b[2mPreparing packages...\u001b[0m (0/6)----\u001b[0m\u001b[0m 14.88 KiB/44.00 KiB \u001b[4A\n",
|
||||
"\u001b[2meval-type-backport\u001b[0m \u001b[32m------------------------------\u001b[2m\u001b[0m\u001b[0m 5.69 KiB/5.69 KiB\n",
|
||||
"\u001b[2mshellingham\u001b[0m \u001b[32m------------------------------\u001b[2m\u001b[0m\u001b[0m 9.53 KiB/9.53 KiB\n",
|
||||
"\u001b[2mtabulate \u001b[0m \u001b[32m-------------\u001b[2m-----------------\u001b[0m\u001b[0m 14.83 KiB/34.43 KiB\n",
|
||||
"\u001b[2K\u001b[4A\u001b[37m⠙\u001b[0m \u001b[2mPreparing packages...\u001b[0m (0/6)----\u001b[0m\u001b[0m 14.88 KiB/44.00 KiB \u001b[4A\n",
|
||||
"\u001b[2meval-type-backport\u001b[0m \u001b[32m------------------------------\u001b[2m\u001b[0m\u001b[0m 5.69 KiB/5.69 KiB\n",
|
||||
"\u001b[2mshellingham\u001b[0m \u001b[32m------------------------------\u001b[2m\u001b[0m\u001b[0m 9.53 KiB/9.53 KiB\n",
|
||||
"\u001b[2mtabulate \u001b[0m \u001b[32m-------------\u001b[2m-----------------\u001b[0m\u001b[0m 14.83 KiB/34.43 KiB\n",
|
||||
"\u001b[2mtyper \u001b[0m \u001b[32m-----------\u001b[2m-------------------\u001b[0m\u001b[0m 14.88 KiB/44.00 KiB\n",
|
||||
"\u001b[2K\u001b[5A\u001b[37m⠙\u001b[0m \u001b[2mPreparing packages...\u001b[0m (0/6)----\u001b[0m\u001b[0m 0 B/85.81 KiB \u001b[5A\n",
|
||||
"\u001b[2meval-type-backport\u001b[0m \u001b[32m------------------------------\u001b[2m\u001b[0m\u001b[0m 5.69 KiB/5.69 KiB\n",
|
||||
"\u001b[2mshellingham\u001b[0m \u001b[32m------------------------------\u001b[2m\u001b[0m\u001b[0m 9.53 KiB/9.53 KiB\n",
|
||||
"\u001b[2mtabulate \u001b[0m \u001b[32m-------------\u001b[2m-----------------\u001b[0m\u001b[0m 14.83 KiB/34.43 KiB\n",
|
||||
"\u001b[2mtyper \u001b[0m \u001b[32m-----------\u001b[2m-------------------\u001b[0m\u001b[0m 14.88 KiB/44.00 KiB\n",
|
||||
"\u001b[2K\u001b[5A\u001b[37m⠙\u001b[0m \u001b[2mPreparing packages...\u001b[0m (0/6)----\u001b[0m\u001b[0m 16.00 KiB/85.81 KiB \u001b[5A\n",
|
||||
"\u001b[2meval-type-backport\u001b[0m \u001b[32m------------------------------\u001b[2m\u001b[0m\u001b[0m 5.69 KiB/5.69 KiB\n",
|
||||
"\u001b[2mshellingham\u001b[0m \u001b[32m------------------------------\u001b[2m\u001b[0m\u001b[0m 9.53 KiB/9.53 KiB\n",
|
||||
"\u001b[2mtabulate \u001b[0m \u001b[32m-------------\u001b[2m-----------------\u001b[0m\u001b[0m 14.83 KiB/34.43 KiB\n",
|
||||
"\u001b[2mtyper \u001b[0m \u001b[32m-----------\u001b[2m-------------------\u001b[0m\u001b[0m 14.88 KiB/44.00 KiB\n",
|
||||
"\u001b[2mtogether \u001b[0m \u001b[32m------\u001b[2m------------------------\u001b[0m\u001b[0m 16.00 KiB/85.81 KiB\n",
|
||||
"\u001b[2K\u001b[6A\u001b[37m⠙\u001b[0m \u001b[2mPreparing packages...\u001b[0m (0/6)----\u001b[0m\u001b[0m 0 B/3.08 MiB \u001b[6A\n",
|
||||
"\u001b[2meval-type-backport\u001b[0m \u001b[32m------------------------------\u001b[2m\u001b[0m\u001b[0m 5.69 KiB/5.69 KiB\n",
|
||||
"\u001b[2mshellingham\u001b[0m \u001b[32m------------------------------\u001b[2m\u001b[0m\u001b[0m 9.53 KiB/9.53 KiB\n",
|
||||
"\u001b[2mtabulate \u001b[0m \u001b[32m-------------\u001b[2m-----------------\u001b[0m\u001b[0m 14.83 KiB/34.43 KiB\n",
|
||||
"\u001b[2mtyper \u001b[0m \u001b[32m-----------\u001b[2m-------------------\u001b[0m\u001b[0m 14.88 KiB/44.00 KiB\n",
|
||||
"\u001b[2mtogether \u001b[0m \u001b[32m------\u001b[2m------------------------\u001b[0m\u001b[0m 16.00 KiB/85.81 KiB\n",
|
||||
"\u001b[2K\u001b[6A\u001b[37m⠙\u001b[0m \u001b[2mPreparing packages...\u001b[0m (0/6)----\u001b[0m\u001b[0m 14.91 KiB/3.08 MiB \u001b[6A\n",
|
||||
"\u001b[2meval-type-backport\u001b[0m \u001b[32m------------------------------\u001b[2m\u001b[0m\u001b[0m 5.69 KiB/5.69 KiB\n",
|
||||
"\u001b[2mshellingham\u001b[0m \u001b[32m------------------------------\u001b[2m\u001b[0m\u001b[0m 9.53 KiB/9.53 KiB\n",
|
||||
"\u001b[2mtabulate \u001b[0m \u001b[32m---------------------------\u001b[2m---\u001b[0m\u001b[0m 30.83 KiB/34.43 KiB\n",
|
||||
"\u001b[2mtyper \u001b[0m \u001b[32m-----------\u001b[2m-------------------\u001b[0m\u001b[0m 14.88 KiB/44.00 KiB\n",
|
||||
"\u001b[2mtogether \u001b[0m \u001b[32m------\u001b[2m------------------------\u001b[0m\u001b[0m 16.00 KiB/85.81 KiB\n",
|
||||
"\u001b[2K\u001b[6A\u001b[37m⠙\u001b[0m \u001b[2mPreparing packages...\u001b[0m (0/6)----\u001b[0m\u001b[0m 14.91 KiB/3.08 MiB \u001b[6A\n",
|
||||
"\u001b[2meval-type-backport\u001b[0m \u001b[32m------------------------------\u001b[2m\u001b[0m\u001b[0m 5.69 KiB/5.69 KiB\n",
|
||||
"\u001b[2mshellingham\u001b[0m \u001b[32m------------------------------\u001b[2m\u001b[0m\u001b[0m 9.53 KiB/9.53 KiB\n",
|
||||
"\u001b[2mtabulate \u001b[0m \u001b[32m------------------------------\u001b[2m\u001b[0m\u001b[0m 34.43 KiB/34.43 KiB\n",
|
||||
"\u001b[2mtyper \u001b[0m \u001b[32m-----------\u001b[2m-------------------\u001b[0m\u001b[0m 14.88 KiB/44.00 KiB\n",
|
||||
"\u001b[2mtogether \u001b[0m \u001b[32m------\u001b[2m------------------------\u001b[0m\u001b[0m 16.00 KiB/85.81 KiB\n",
|
||||
"\u001b[2K\u001b[6A\u001b[37m⠙\u001b[0m \u001b[2mPreparing packages...\u001b[0m (0/6)----\u001b[0m\u001b[0m 14.91 KiB/3.08 MiB \u001b[6A\n",
|
||||
"\u001b[2mshellingham\u001b[0m \u001b[32m------------------------------\u001b[2m\u001b[0m\u001b[0m 9.53 KiB/9.53 KiB\n",
|
||||
"\u001b[2mtabulate \u001b[0m \u001b[32m------------------------------\u001b[2m\u001b[0m\u001b[0m 34.43 KiB/34.43 KiB\n",
|
||||
"\u001b[2mtyper \u001b[0m \u001b[32m-----------\u001b[2m-------------------\u001b[0m\u001b[0m 14.88 KiB/44.00 KiB\n",
|
||||
"\u001b[2mtogether \u001b[0m \u001b[32m------\u001b[2m------------------------\u001b[0m\u001b[0m 16.00 KiB/85.81 KiB\n",
|
||||
"\u001b[2K\u001b[5A\u001b[37m⠙\u001b[0m \u001b[2mPreparing packages...\u001b[0m (0/6)----\u001b[0m\u001b[0m 14.91 KiB/3.08 MiB \u001b[5A\n",
|
||||
"\u001b[2mshellingham\u001b[0m \u001b[32m------------------------------\u001b[2m\u001b[0m\u001b[0m 9.53 KiB/9.53 KiB\n",
|
||||
"\u001b[2mtabulate \u001b[0m \u001b[32m------------------------------\u001b[2m\u001b[0m\u001b[0m 34.43 KiB/34.43 KiB\n",
|
||||
"\u001b[2mtyper \u001b[0m \u001b[32m-----------\u001b[2m-------------------\u001b[0m\u001b[0m 14.88 KiB/44.00 KiB\n",
|
||||
"\u001b[2mtogether \u001b[0m \u001b[32m------\u001b[2m------------------------\u001b[0m\u001b[0m 16.00 KiB/85.81 KiB\n",
|
||||
"\u001b[2K\u001b[5A\u001b[37m⠙\u001b[0m \u001b[2mPreparing packages...\u001b[0m (0/6)----\u001b[0m\u001b[0m 30.91 KiB/3.08 MiB \u001b[5A\n",
|
||||
"\u001b[2mshellingham\u001b[0m \u001b[32m------------------------------\u001b[2m\u001b[0m\u001b[0m 9.53 KiB/9.53 KiB\n",
|
||||
"\u001b[2mtyper \u001b[0m \u001b[32m-----------\u001b[2m-------------------\u001b[0m\u001b[0m 14.88 KiB/44.00 KiB\n",
|
||||
"\u001b[2mtogether \u001b[0m \u001b[32m------\u001b[2m------------------------\u001b[0m\u001b[0m 16.00 KiB/85.81 KiB\n",
|
||||
"\u001b[2K\u001b[4A\u001b[37m⠙\u001b[0m \u001b[2mPreparing packages...\u001b[0m (0/6)----\u001b[0m\u001b[0m 30.91 KiB/3.08 MiB \u001b[4A\n",
|
||||
"\u001b[2mshellingham\u001b[0m \u001b[32m------------------------------\u001b[2m\u001b[0m\u001b[0m 9.53 KiB/9.53 KiB\n",
|
||||
"\u001b[2mtyper \u001b[0m \u001b[32m-----------\u001b[2m-------------------\u001b[0m\u001b[0m 14.88 KiB/44.00 KiB\n",
|
||||
"\u001b[2mtogether \u001b[0m \u001b[32m------\u001b[2m------------------------\u001b[0m\u001b[0m 16.00 KiB/85.81 KiB\n",
|
||||
"\u001b[2K\u001b[4A\u001b[37m⠙\u001b[0m \u001b[2mPreparing packages...\u001b[0m (0/6)----\u001b[0m\u001b[0m 46.91 KiB/3.08 MiB \u001b[4A\n",
|
||||
"\u001b[2mshellingham\u001b[0m \u001b[32m------------------------------\u001b[2m\u001b[0m\u001b[0m 9.53 KiB/9.53 KiB\n",
|
||||
"\u001b[2mtyper \u001b[0m \u001b[32m-----------\u001b[2m-------------------\u001b[0m\u001b[0m 14.88 KiB/44.00 KiB\n",
|
||||
"\u001b[2mtogether \u001b[0m \u001b[32m------\u001b[2m------------------------\u001b[0m\u001b[0m 16.00 KiB/85.81 KiB\n",
|
||||
"\u001b[2K\u001b[4A\u001b[37m⠙\u001b[0m \u001b[2mPreparing packages...\u001b[0m (0/6)----\u001b[0m\u001b[0m 62.91 KiB/3.08 MiB \u001b[4A\n",
|
||||
"\u001b[2mshellingham\u001b[0m \u001b[32m------------------------------\u001b[2m\u001b[0m\u001b[0m 9.53 KiB/9.53 KiB\n",
|
||||
"\u001b[2mtyper \u001b[0m \u001b[32m-----------\u001b[2m-------------------\u001b[0m\u001b[0m 14.88 KiB/44.00 KiB\n",
|
||||
"\u001b[2mtogether \u001b[0m \u001b[32m------\u001b[2m------------------------\u001b[0m\u001b[0m 16.00 KiB/85.81 KiB\n",
|
||||
"\u001b[2K\u001b[4A\u001b[37m⠙\u001b[0m \u001b[2mPreparing packages...\u001b[0m (0/6)----\u001b[0m\u001b[0m 78.91 KiB/3.08 MiB \u001b[4A\n",
|
||||
"\u001b[2mshellingham\u001b[0m \u001b[32m------------------------------\u001b[2m\u001b[0m\u001b[0m 9.53 KiB/9.53 KiB\n",
|
||||
"\u001b[2mtyper \u001b[0m \u001b[32m-----------\u001b[2m-------------------\u001b[0m\u001b[0m 14.88 KiB/44.00 KiB\n",
|
||||
"\u001b[2mtogether \u001b[0m \u001b[32m------\u001b[2m------------------------\u001b[0m\u001b[0m 16.00 KiB/85.81 KiB\n",
|
||||
"\u001b[2K\u001b[4A\u001b[37m⠙\u001b[0m \u001b[2mPreparing packages...\u001b[0m (0/6)----\u001b[0m\u001b[0m 94.91 KiB/3.08 MiB \u001b[4A\n",
|
||||
"\u001b[2mshellingham\u001b[0m \u001b[32m------------------------------\u001b[2m\u001b[0m\u001b[0m 9.53 KiB/9.53 KiB\n",
|
||||
"\u001b[2mtyper \u001b[0m \u001b[32m-----------\u001b[2m-------------------\u001b[0m\u001b[0m 14.88 KiB/44.00 KiB\n",
|
||||
"\u001b[2mtogether \u001b[0m \u001b[32m------------\u001b[2m------------------\u001b[0m\u001b[0m 32.00 KiB/85.81 KiB\n",
|
||||
"\u001b[2K\u001b[4A\u001b[37m⠙\u001b[0m \u001b[2mPreparing packages...\u001b[0m (0/6)----\u001b[0m\u001b[0m 2.62 MiB/3.08 MiB \u001b[4A\n",
|
||||
"\u001b[2mtyper \u001b[0m \u001b[32m----------------------\u001b[2m--------\u001b[0m\u001b[0m 30.88 KiB/44.00 KiB\n",
|
||||
"\u001b[2mtogether \u001b[0m \u001b[32m------------\u001b[2m------------------\u001b[0m\u001b[0m 32.00 KiB/85.81 KiB\n",
|
||||
"\u001b[2K\u001b[3A\u001b[37m⠹\u001b[0m \u001b[2mPreparing packages...\u001b[0m (3/6)----\u001b[0m\u001b[0m 2.62 MiB/3.08 MiB \u001b[3A\n",
|
||||
"\u001b[2mtyper \u001b[0m \u001b[32m------------------------------\u001b[2m\u001b[0m\u001b[0m 44.00 KiB/44.00 KiB\n",
|
||||
"\u001b[2mtogether \u001b[0m \u001b[32m------------\u001b[2m------------------\u001b[0m\u001b[0m 32.00 KiB/85.81 KiB\n",
|
||||
"\u001b[2K\u001b[3A\u001b[37m⠹\u001b[0m \u001b[2mPreparing packages...\u001b[0m (3/6)----\u001b[0m\u001b[0m 2.62 MiB/3.08 MiB \u001b[3A\n",
|
||||
"\u001b[2mtogether \u001b[0m \u001b[32m------------\u001b[2m------------------\u001b[0m\u001b[0m 32.00 KiB/85.81 KiB\n",
|
||||
"\u001b[2K\u001b[2A\u001b[37m⠹\u001b[0m \u001b[2mPreparing packages...\u001b[0m (3/6)2m--\u001b[0m\u001b[0m 2.80 MiB/3.08 MiB \u001b[2A\n",
|
||||
"\u001b[2mtogether \u001b[0m \u001b[32m-----------------\u001b[2m-------------\u001b[0m\u001b[0m 48.00 KiB/85.81 KiB\n",
|
||||
"\u001b[2K\u001b[2A\u001b[37m⠹\u001b[0m \u001b[2mPreparing packages...\u001b[0m (3/6)2m--\u001b[0m\u001b[0m 2.81 MiB/3.08 MiB \u001b[2A\n",
|
||||
"\u001b[2K\u001b[1A\u001b[37m⠹\u001b[0m \u001b[2mPreparing packages...\u001b[0m (3/6)----\u001b[0m\u001b[0m 48.00 KiB/85.81 KiB \u001b[1A\n",
|
||||
"\u001b[2K\u001b[1A\u001b[37m⠹\u001b[0m \u001b[2mPreparing packages...\u001b[0m (3/6)2m--\u001b[0m\u001b[0m 80.00 KiB/85.81 KiB \u001b[1A\n",
|
||||
"\u001b[2K\u001b[2mPrepared \u001b[1m6 packages\u001b[0m \u001b[2min 365ms\u001b[0m\u001b[0m \u001b[1A\n",
|
||||
"\u001b[2K\u001b[2mInstalled \u001b[1m6 packages\u001b[0m \u001b[2min 50ms\u001b[0m\u001b[0m \u001b[0m\n",
|
||||
" \u001b[32m+\u001b[39m \u001b[1meval-type-backport\u001b[0m\u001b[2m==0.2.2\u001b[0m\n",
|
||||
" \u001b[32m+\u001b[39m \u001b[1mfaiss-cpu\u001b[0m\u001b[2m==1.10.0\u001b[0m\n",
|
||||
" \u001b[32m+\u001b[39m \u001b[1mshellingham\u001b[0m\u001b[2m==1.5.4\u001b[0m\n",
|
||||
" \u001b[32m+\u001b[39m \u001b[1mtabulate\u001b[0m\u001b[2m==0.9.0\u001b[0m\n",
|
||||
" \u001b[32m+\u001b[39m \u001b[1mtogether\u001b[0m\u001b[2m==1.5.5\u001b[0m\n",
|
||||
" \u001b[32m+\u001b[39m \u001b[1mtyper\u001b[0m\u001b[2m==0.15.2\u001b[0m\n",
|
||||
"torch torchvision --index-url https://download.pytorch.org/whl/cpu\n",
|
||||
"\u001b[2mUsing Python 3.11.11 environment at: /Users/erichuang/projects/internal-llama-stack/.venv\u001b[0m\n",
|
||||
"\u001b[2mAudited \u001b[1m2 packages\u001b[0m \u001b[2min 32ms\u001b[0m\u001b[0m\n",
|
||||
"sentence-transformers --no-deps\n",
|
||||
"\u001b[2mUsing Python 3.11.11 environment at: /Users/erichuang/projects/internal-llama-stack/.venv\u001b[0m\n",
|
||||
"\u001b[2mAudited \u001b[1m1 package\u001b[0m \u001b[2min 63ms\u001b[0m\u001b[0m\n",
|
||||
"\u001b[32mBuild Successful!\u001b[0m\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"import os\n",
|
||||
"import subprocess\n",
|
||||
"import time\n",
|
||||
"\n",
|
||||
"!uv pip install requests\n",
|
||||
"\n",
|
||||
"if \"UV_SYSTEM_PYTHON\" in os.environ:\n",
|
||||
" del os.environ[\"UV_SYSTEM_PYTHON\"]\n",
|
||||
"\n",
|
||||
"# this command installs all the dependencies needed for the llama stack server\n",
|
||||
"!uv run --with llama-stack llama stack build --distro meta-reference-gpu --image-type venv\n",
|
||||
"\n",
|
||||
"def run_llama_stack_server_background():\n",
|
||||
" log_file = open(\"llama_stack_server.log\", \"w\")\n",
|
||||
" process = subprocess.Popen(\n",
|
||||
" f\"INFERENCE_MODEL={model_id} uv run --with llama-stack llama stack run meta-reference-gpu --image-type venv\",\n",
|
||||
" shell=True,\n",
|
||||
" stdout=log_file,\n",
|
||||
" stderr=log_file,\n",
|
||||
" text=True\n",
|
||||
" )\n",
|
||||
"\n",
|
||||
" print(f\"Starting Llama Stack server with PID: {process.pid}\")\n",
|
||||
" return process\n",
|
||||
"\n",
|
||||
"def wait_for_server_to_start():\n",
|
||||
" import requests\n",
|
||||
" from requests.exceptions import ConnectionError\n",
|
||||
" import time\n",
|
||||
"\n",
|
||||
" url = \"http://0.0.0.0:8321/v1/health\"\n",
|
||||
" max_retries = 30\n",
|
||||
" retry_interval = 1\n",
|
||||
"\n",
|
||||
" print(\"Waiting for server to start\", end=\"\")\n",
|
||||
" for _ in range(max_retries):\n",
|
||||
" try:\n",
|
||||
" response = requests.get(url)\n",
|
||||
" if response.status_code == 200:\n",
|
||||
" print(\"\\nServer is ready!\")\n",
|
||||
" return True\n",
|
||||
" except ConnectionError:\n",
|
||||
" print(\".\", end=\"\", flush=True)\n",
|
||||
" time.sleep(retry_interval)\n",
|
||||
"\n",
|
||||
" print(\"\\nServer failed to start after\", max_retries * retry_interval, \"seconds\")\n",
|
||||
" return False\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"# use this helper if needed to kill the server\n",
|
||||
"def kill_llama_stack_server():\n",
|
||||
" # Kill any existing llama stack server processes\n",
|
||||
" os.system(\"ps aux | grep -v grep | grep llama_stack.core.server.server | awk '{print $2}' | xargs kill -9\")\n"
|
||||
]
|
||||
"outputs": [],
|
||||
"source": "import os\nimport subprocess\nimport time\n\n!uv pip install requests\n\nif \"UV_SYSTEM_PYTHON\" in os.environ:\n del os.environ[\"UV_SYSTEM_PYTHON\"]\n\n# this command installs all the dependencies needed for the llama stack server\n!uv run --with llama-stack llama stack build --distro meta-reference-gpu --image-type venv\n\ndef run_llama_stack_server_background():\n log_file = open(\"llama_stack_server.log\", \"w\")\n process = subprocess.Popen(\n f\"INFERENCE_MODEL={model_id} uv run --with llama-stack llama stack run meta-reference-gpu\",\n shell=True,\n stdout=log_file,\n stderr=log_file,\n text=True\n )\n\n print(f\"Starting Llama Stack server with PID: {process.pid}\")\n return process\n\ndef wait_for_server_to_start():\n import requests\n from requests.exceptions import ConnectionError\n import time\n\n url = \"http://0.0.0.0:8321/v1/health\"\n max_retries = 30\n retry_interval = 1\n\n print(\"Waiting for server to start\", end=\"\")\n for _ in range(max_retries):\n try:\n response = requests.get(url)\n if response.status_code == 200:\n print(\"\\nServer is ready!\")\n return True\n except ConnectionError:\n print(\".\", end=\"\", flush=True)\n time.sleep(retry_interval)\n\n print(\"\\nServer failed to start after\", max_retries * retry_interval, \"seconds\")\n return False\n\n\n# use this helper if needed to kill the server\ndef kill_llama_stack_server():\n # Kill any existing llama stack server processes\n os.system(\"ps aux | grep -v grep | grep llama_stack.core.server.server | awk '{print $2}' | xargs kill -9\")\n"
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
|
|
|
|||
|
|
@ -88,7 +88,7 @@ If you're looking for more specific topics, we have a [Zero to Hero Guide](#next
|
|||
...
|
||||
Build Successful!
|
||||
You can find the newly-built template here: ~/.llama/distributions/starter/starter-run.yaml
|
||||
You can run the new Llama Stack Distro via: uv run --with llama-stack llama stack run starter --image-type venv
|
||||
You can run the new Llama Stack Distro via: uv run --with llama-stack llama stack run starter
|
||||
```
|
||||
|
||||
3. **Set the ENV variables by exporting them to the terminal**:
|
||||
|
|
@ -106,7 +106,6 @@ If you're looking for more specific topics, we have a [Zero to Hero Guide](#next
|
|||
SAFETY_MODEL=$SAFETY_MODEL \
|
||||
OLLAMA_URL=$OLLAMA_URL \
|
||||
uv run --with llama-stack llama stack run starter \
|
||||
--image-type venv \
|
||||
--port $LLAMA_STACK_PORT
|
||||
```
|
||||
Note: Every time you run a new model with `ollama run`, you will need to restart the llama stack. Otherwise it won't see the new model.
|
||||
|
|
|
|||
|
|
@ -55,12 +55,12 @@ class StackRun(Subcommand):
|
|||
"--image-name",
|
||||
type=str,
|
||||
default=None,
|
||||
help="Name of the image to run. Defaults to the current environment",
|
||||
help="[DEPRECATED] This flag is no longer supported. Please activate your virtual environment before running.",
|
||||
)
|
||||
self.parser.add_argument(
|
||||
"--image-type",
|
||||
type=str,
|
||||
help="Image Type used during the build. This can be only venv.",
|
||||
help="[DEPRECATED] This flag is no longer supported. Please activate your virtual environment before running.",
|
||||
choices=[e.value for e in ImageType if e.value != ImageType.CONTAINER.value],
|
||||
)
|
||||
self.parser.add_argument(
|
||||
|
|
@ -106,11 +106,18 @@ class StackRun(Subcommand):
|
|||
import yaml
|
||||
|
||||
from llama_stack.core.configure import parse_and_maybe_upgrade_config
|
||||
from llama_stack.core.utils.exec import formulate_run_args, run_command
|
||||
|
||||
if args.image_type or args.image_name:
|
||||
self.parser.error(
|
||||
"The --image-type and --image-name flags are no longer supported.\n\n"
|
||||
"Please activate your virtual environment manually before running `llama stack run`.\n\n"
|
||||
"For example:\n"
|
||||
" source /path/to/venv/bin/activate\n"
|
||||
" llama stack run <config>\n"
|
||||
)
|
||||
|
||||
if args.enable_ui:
|
||||
self._start_ui_development_server(args.port)
|
||||
image_type, image_name = args.image_type, args.image_name
|
||||
|
||||
if args.config:
|
||||
try:
|
||||
|
|
@ -122,10 +129,6 @@ class StackRun(Subcommand):
|
|||
else:
|
||||
config_file = None
|
||||
|
||||
# Check if config is required based on image type
|
||||
if image_type == ImageType.VENV.value and not config_file:
|
||||
self.parser.error("Config file is required for venv environment")
|
||||
|
||||
if config_file:
|
||||
logger.info(f"Using run configuration: {config_file}")
|
||||
|
||||
|
|
@ -140,23 +143,8 @@ class StackRun(Subcommand):
|
|||
os.makedirs(str(config.external_providers_dir), exist_ok=True)
|
||||
except AttributeError as e:
|
||||
self.parser.error(f"failed to parse config file '{config_file}':\n {e}")
|
||||
else:
|
||||
config = None
|
||||
|
||||
# If neither image type nor image name is provided, assume the server should be run directly
|
||||
# using the current environment packages.
|
||||
if not image_type and not image_name:
|
||||
logger.info("No image type or image name provided. Assuming environment packages.")
|
||||
self._uvicorn_run(config_file, args)
|
||||
else:
|
||||
run_args = formulate_run_args(image_type, image_name)
|
||||
|
||||
run_args.extend([str(args.port)])
|
||||
|
||||
if config_file:
|
||||
run_args.extend(["--config", str(config_file)])
|
||||
|
||||
run_command(run_args)
|
||||
|
||||
def _uvicorn_run(self, config_file: Path | None, args: argparse.Namespace) -> None:
|
||||
if not config_file:
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue