phoenix-oss/llama-stack
1
0
Fork 0
forked from phoenix-oss/llama-stack-mirror
Code Pull requests Releases Packages 2 Activity Actions

Kill --name from llama stack build (#340)

Browse source
This commit is contained in:
Ashwin Bharambe 2024-10-28 23:07:32 -07:00 • committed by GitHub
parent 26d1668f7d
commit 4aa1bf6a60
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
9 changed files with 71 additions and 130 deletions
Download patch file Download diff file Expand all files Collapse all files

26
docs/building_distro.md
View file

@ -58,15 +58,15 @@ llama stack build --list-templates
You may then pick a template to build your distribution with providers fitted to your liking.
```
llama stack build --template local-tgi --name my-tgi-stack
llama stack build --template tgi
```
```
$ llama stack build --template local-tgi --name my-tgi-stack
$ llama stack build --template tgi
...
...
Build spec configuration saved at ~/.conda/envs/llamastack-my-tgi-stack/my-tgi-stack-build.yaml
You may now run `llama stack configure my-tgi-stack` or `llama stack configure ~/.conda/envs/llamastack-my-tgi-stack/my-tgi-stack-build.yaml`
Build spec configuration saved at ~/.conda/envs/llamastack-tgi/tgi-build.yaml
You may now run `llama stack configure tgi` or `llama stack configure ~/.conda/envs/llamastack-tgi/tgi-build.yaml`
```
#### Building from config file
@ -75,9 +75,9 @@ You may now run `llama stack configure my-tgi-stack` or `llama stack configure ~
- The config file will be of contents like the ones in `llama_stack/distributions/templates/`.
```
$ cat llama_stack/distribution/templates/local-ollama-build.yaml
$ cat llama_stack/templates/ollama/build.yaml
name: local-ollama
name: ollama
distribution_spec:
description: Like local, but use ollama for running LLM inference
providers:
@ -90,7 +90,7 @@ image_type: conda
```
```
llama stack build --config llama_stack/distribution/templates/local-ollama-build.yaml
llama stack build --config llama_stack/templates/ollama/build.yaml
```
#### How to build distribution with Docker image
@ -101,7 +101,7 @@ llama stack build --config llama_stack/distribution/templates/local-ollama-build
To build a docker image, you may start off from a template and use the `--image-type docker` flag to specify `docker` as the build image type.
```
llama stack build --template local --image-type docker --name docker-0
llama stack build --template local --image-type docker
```
Alternatively, you may use a config file and set `image_type` to `docker` in our `<name>-build.yaml` file, and run `llama stack build <name>-build.yaml`. The `<name>-build.yaml` will be of contents like:
@ -136,14 +136,14 @@ Build spec configuration saved at ~/.llama/distributions/docker/docker-local-bui
## Step 2. Configure
After our distribution is built (either in form of docker or conda environment), we will run the following command to
```
llama stack configure [ <name> | <docker-image-name> | <path/to/name.build.yaml>]
llama stack configure [ <docker-image-name> | <path/to/name.build.yaml>]
```
- For `conda` environments: <path/to/name.build.yaml> would be the generated build spec saved from Step 1.
- For `docker` images downloaded from Dockerhub, you could also use <docker-image-name> as the argument.
- Run `docker images` to check list of available images on your machine.
```
$ llama stack configure 8b-instruct
$ llama stack configure tgi
Configuring API: inference (meta-reference)
Enter value for model (existing: Meta-Llama3.1-8B-Instruct) (required):
@ -172,10 +172,10 @@ Enter value for wolfram_api_key (optional):
Configuring API: telemetry (console)
YAML configuration has been written to ~/.llama/builds/conda/8b-instruct-run.yaml
YAML configuration has been written to ~/.llama/builds/conda/tgi-run.yaml
```
After this step is successful, you should be able to find a run configuration spec in `~/.llama/builds/conda/8b-instruct-run.yaml` with the following contents. You may edit this file to change the settings.
After this step is successful, you should be able to find a run configuration spec in `~/.llama/builds/conda/tgi-run.yaml` with the following contents. You may edit this file to change the settings.
As you can see, we did basic configuration above and configured:
- inference to run on model `Meta-Llama3.1-8B-Instruct` (obtained from `llama model list`)
@ -228,7 +228,7 @@ INFO: Uvicorn running on http://[::]:5000 (Press CTRL+C to quit)
```
> [!NOTE]
> Configuration is in `~/.llama/builds/local/conda/8b-instruct-run.yaml`. Feel free to increase `max_seq_len`.
> Configuration is in `~/.llama/builds/local/conda/tgi-run.yaml`. Feel free to increase `max_seq_len`.
> [!IMPORTANT]
> The "local" distribution inference server currently only supports CUDA. It will not work on Apple Silicon machines.

26
docs/cli_reference.md
View file

@ -229,8 +229,8 @@ You will be shown a Markdown formatted description of the model interface and ho
- Please see our [Getting Started](getting_started.md) guide for more details on how to build and start a Llama Stack distribution.
### Step 3.1 Build
In the following steps, imagine we'll be working with a `Llama3.1-8B-Instruct` model. We will name our build `8b-instruct` to help us remember the config. We will start build our distribution (in the form of a Conda environment, or Docker image). In this step, we will specify:
- `name`: the name for our distribution (e.g. `8b-instruct`)
In the following steps, imagine we'll be working with a `Llama3.1-8B-Instruct` model. We will name our build `tgi` to help us remember the config. We will start build our distribution (in the form of a Conda environment, or Docker image). In this step, we will specify:
- `name`: the name for our distribution (e.g. `tgi`)
- `image_type`: our build image type (`conda | docker`)
- `distribution_spec`: our distribution specs for specifying API providers
- `description`: a short description of the configurations for the distribution
@ -279,15 +279,15 @@ llama stack build --list-templates
You may then pick a template to build your distribution with providers fitted to your liking.
```
llama stack build --template local-tgi --name my-tgi-stack --image-type conda
llama stack build --template tgi --image-type conda
```
```
$ llama stack build --template local-tgi --name my-tgi-stack --image-type conda
$ llama stack build --template tgi --image-type conda
...
...
Build spec configuration saved at ~/.conda/envs/llamastack-my-tgi-stack/my-tgi-stack-build.yaml
You may now run `llama stack configure my-tgi-stack` or `llama stack configure ~/.conda/envs/llamastack-my-tgi-stack/my-tgi-stack-build.yaml`
Build spec configuration saved at ~/.conda/envs/llamastack-tgi/tgi-build.yaml
You may now run `llama stack configure tgi` or `llama stack configure ~/.conda/envs/llamastack-tgi/tgi-build.yaml`
```
#### Building from config file
@ -298,7 +298,7 @@ You may now run `llama stack configure my-tgi-stack` or `llama stack configure ~
```
$ cat build.yaml
name: local-ollama
name: ollama
distribution_spec:
description: Like local, but use ollama for running LLM inference
providers:
@ -319,7 +319,7 @@ llama stack build --config build.yaml
To build a docker image, you may start off from a template and use the `--image-type docker` flag to specify `docker` as the build image type.
```
llama stack build --template local --image-type docker --name docker-0
llama stack build --template tgi --image-type docker
```
Alternatively, you may use a config file and set `image_type` to `docker` in our `<name>-build.yaml` file, and run `llama stack build <name>-build.yaml`. The `<name>-build.yaml` will be of contents like:
@ -354,14 +354,14 @@ Build spec configuration saved at ~/.llama/distributions/docker/docker-local-bui
### Step 3.2 Configure
After our distribution is built (either in form of docker or conda environment), we will run the following command to
```
llama stack configure [ <name> | <docker-image-name> | <path/to/name.build.yaml>]
llama stack configure [ <docker-image-name> | <path/to/name-build.yaml>]
```
- For `conda` environments: <path/to/name.build.yaml> would be the generated build spec saved from Step 1.
- For `docker` images downloaded from Dockerhub, you could also use <docker-image-name> as the argument.
- Run `docker images` to check list of available images on your machine.
```
$ llama stack configure ~/.llama/distributions/conda/8b-instruct-build.yaml
$ llama stack configure ~/.llama/distributions/conda/tgi-build.yaml
Configuring API: inference (meta-reference)
Enter value for model (existing: Llama3.1-8B-Instruct) (required):
@ -409,13 +409,13 @@ Note that all configurations as well as models are stored in `~/.llama`
Now, let's start the Llama Stack Distribution Server. You will need the YAML configuration file which was written out at the end by the `llama stack configure` step.
```
llama stack run ~/.llama/builds/conda/8b-instruct-run.yaml
llama stack run ~/.llama/builds/conda/tgi-run.yaml
```
You should see the Llama Stack server start and print the APIs that it is supporting
```
$ llama stack run ~/.llama/builds/local/conda/8b-instruct.yaml
$ llama stack run ~/.llama/builds/local/conda/tgi-run.yaml
> initializing model parallel with size 1
> initializing ddp with size 1
@ -446,7 +446,7 @@ INFO: Uvicorn running on http://[::]:5000 (Press CTRL+C to quit)
```
> [!NOTE]
> Configuration is in `~/.llama/builds/local/conda/8b-instruct-run.yaml`. Feel free to increase `max_seq_len`.
> Configuration is in `~/.llama/builds/local/conda/tgi-run.yaml`. Feel free to increase `max_seq_len`.
> [!IMPORTANT]
> The "local" distribution inference server currently only supports CUDA. It will not work on Apple Silicon machines.

1
docs/getting_started.ipynb
View file

@ -68,7 +68,6 @@
"```\n",
"$ llama stack configure llamastack-local-gpu\n",
"\n",
"Could not find llamastack-local-gpu. Trying conda build name instead...\n",
"Could not find /home/hjshah/.conda/envs/llamastack-llamastack-local-gpu/llamastack-local-gpu-build.yaml. Trying docker image name instead...\n",
"+ podman run --network host -it -v /home/hjshah/.llama/builds/docker:/app/builds llamastack-local-gpu llama stack configure ./llamastack-build.yaml --output-dir /app/builds\n",
"\n",

1
docs/getting_started.md
View file

@ -97,7 +97,6 @@ docker run -it -p 5000:5000 -v ~/.llama:/root/.llama -v ./run.yaml:/root/my-run.
```
$ llama stack configure my-local-stack
Could not find my-local-stack. Trying conda build name instead...
Configuring API `inference`...
=== Configuring provider `meta-reference` for API inference...
Enter value for model (default: Llama3.1-8B-Instruct) (required):

30
docs/source/cli_reference.md
View file

@ -279,15 +279,15 @@ llama stack build --list-templates
You may then pick a template to build your distribution with providers fitted to your liking.
```
llama stack build --template local-tgi --name my-tgi-stack
llama stack build --template tgi
```
```
$ llama stack build --template local-tgi --name my-tgi-stack
$ llama stack build --template tgi
...
...
Build spec configuration saved at ~/.conda/envs/llamastack-my-tgi-stack/my-tgi-stack-build.yaml
You may now run `llama stack configure my-tgi-stack` or `llama stack configure ~/.conda/envs/llamastack-my-tgi-stack/my-tgi-stack-build.yaml`
Build spec configuration saved at ~/.conda/envs/llamastack-tgi/tgi-build.yaml
You may now run `llama stack configure tgi` or `llama stack configure ~/.conda/envs/llamastack-tgi/tgi-build.yaml`
```
#### Building from config file
@ -296,9 +296,9 @@ You may now run `llama stack configure my-tgi-stack` or `llama stack configure ~
- The config file will be of contents like the ones in `llama_stack/distributions/templates/`.
```
$ cat llama_stack/distribution/templates/local-ollama-build.yaml
$ cat llama_stack/templates/ollama/build.yaml
name: local-ollama
name: ollama
distribution_spec:
description: Like local, but use ollama for running LLM inference
providers:
@ -311,7 +311,7 @@ image_type: conda
```
```
llama stack build --config llama_stack/distribution/templates/local-ollama-build.yaml
llama stack build --config llama_stack/templates/ollama/build.yaml
```
#### How to build distribution with Docker image
@ -319,7 +319,7 @@ llama stack build --config llama_stack/distribution/templates/local-ollama-build
To build a docker image, you may start off from a template and use the `--image-type docker` flag to specify `docker` as the build image type.
```
llama stack build --template local --image-type docker --name docker-0
llama stack build --template local --image-type docker
```
Alternatively, you may use a config file and set `image_type` to `docker` in our `<name>-build.yaml` file, and run `llama stack build <name>-build.yaml`. The `<name>-build.yaml` will be of contents like:
@ -354,14 +354,14 @@ Build spec configuration saved at ~/.llama/distributions/docker/docker-local-bui
### Step 3.2 Configure
After our distribution is built (either in form of docker or conda environment), we will run the following command to
```
llama stack configure [ <name> | <docker-image-name> | <path/to/name.build.yaml>]
llama stack configure [ <docker-image-name> | <path/to/name.build.yaml>]
```
- For `conda` environments: <path/to/name.build.yaml> would be the generated build spec saved from Step 1.
- For `docker` images downloaded from Dockerhub, you could also use <docker-image-name> as the argument.
- Run `docker images` to check list of available images on your machine.
```
$ llama stack configure ~/.llama/distributions/conda/8b-instruct-build.yaml
$ llama stack configure ~/.llama/distributions/conda/tgi-build.yaml
Configuring API: inference (meta-reference)
Enter value for model (existing: Llama3.1-8B-Instruct) (required):
@ -390,10 +390,10 @@ Enter value for wolfram_api_key (optional):
Configuring API: telemetry (console)
YAML configuration has been written to ~/.llama/builds/conda/8b-instruct-run.yaml
YAML configuration has been written to ~/.llama/builds/conda/tgi-run.yaml
```
After this step is successful, you should be able to find a run configuration spec in `~/.llama/builds/conda/8b-instruct-run.yaml` with the following contents. You may edit this file to change the settings.
After this step is successful, you should be able to find a run configuration spec in `~/.llama/builds/conda/tgi-run.yaml` with the following contents. You may edit this file to change the settings.
As you can see, we did basic configuration above and configured:
- inference to run on model `Llama3.1-8B-Instruct` (obtained from `llama model list`)
@ -409,13 +409,13 @@ Note that all configurations as well as models are stored in `~/.llama`
Now, let's start the Llama Stack Distribution Server. You will need the YAML configuration file which was written out at the end by the `llama stack configure` step.
```
llama stack run ~/.llama/builds/conda/8b-instruct-run.yaml
llama stack run ~/.llama/builds/conda/tgi-run.yaml
```
You should see the Llama Stack server start and print the APIs that it is supporting
```
$ llama stack run ~/.llama/builds/local/conda/8b-instruct.yaml
$ llama stack run ~/.llama/builds/conda/tgi-run.yaml
> initializing model parallel with size 1
> initializing ddp with size 1
@ -446,7 +446,7 @@ INFO: Uvicorn running on http://[::]:5000 (Press CTRL+C to quit)
```
> [!NOTE]
> Configuration is in `~/.llama/builds/local/conda/8b-instruct-run.yaml`. Feel free to increase `max_seq_len`.
> Configuration is in `~/.llama/builds/local/conda/tgi-run.yaml`. Feel free to increase `max_seq_len`.
> [!IMPORTANT]
> The "local" distribution inference server currently only supports CUDA. It will not work on Apple Silicon machines.

29
docs/source/getting_started.md
View file

@ -86,7 +86,6 @@ llama stack configure <name>
```
$ llama stack configure my-local-stack
Could not find my-local-stack. Trying conda build name instead...
Configuring API `inference`...
=== Configuring provider `meta-reference` for API inference...
Enter value for model (default: Llama3.1-8B-Instruct) (required):
@ -218,15 +217,15 @@ llama stack build --list-templates
You may then pick a template to build your distribution with providers fitted to your liking.
```
llama stack build --template local-tgi --name my-tgi-stack
llama stack build --template tgi
```
```
$ llama stack build --template local-tgi --name my-tgi-stack
$ llama stack build --template tgi
...
...
Build spec configuration saved at ~/.conda/envs/llamastack-my-tgi-stack/my-tgi-stack-build.yaml
You may now run `llama stack configure my-tgi-stack` or `llama stack configure ~/.conda/envs/llamastack-my-tgi-stack/my-tgi-stack-build.yaml`
Build spec configuration saved at ~/.conda/envs/llamastack-tgi/tgi-build.yaml
You may now run `llama stack configure tgi` or `llama stack configure ~/.conda/envs/llamastack-tgi/tgi-build.yaml`
```
#### Building from config file
@ -235,9 +234,9 @@ You may now run `llama stack configure my-tgi-stack` or `llama stack configure ~
- The config file will be of contents like the ones in `llama_stack/distributions/templates/`.
```
$ cat llama_stack/distribution/templates/local-ollama-build.yaml
$ cat llama_stack/templates/ollama/build.yaml
name: local-ollama
name: ollama
distribution_spec:
description: Like local, but use ollama for running LLM inference
providers:
@ -250,7 +249,7 @@ image_type: conda
```
```
llama stack build --config llama_stack/distribution/templates/local-ollama-build.yaml
llama stack build --config llama_stack/templates/ollama/build.yaml
```
#### How to build distribution with Docker image
@ -261,7 +260,7 @@ llama stack build --config llama_stack/distribution/templates/local-ollama-build
To build a docker image, you may start off from a template and use the `--image-type docker` flag to specify `docker` as the build image type.
```
llama stack build --template local --image-type docker --name docker-0
llama stack build --template tgi --image-type docker
```
Alternatively, you may use a config file and set `image_type` to `docker` in our `<name>-build.yaml` file, and run `llama stack build <name>-build.yaml`. The `<name>-build.yaml` will be of contents like:
@ -296,14 +295,14 @@ Build spec configuration saved at ~/.llama/distributions/docker/docker-local-bui
### Step 2. Configure
After our distribution is built (either in form of docker or conda environment), we will run the following command to
```
llama stack configure [ <name> | <docker-image-name> | <path/to/name.build.yaml>]
llama stack configure [ <docker-image-name> | <path/to/name.build.yaml>]
```
- For `conda` environments: <path/to/name.build.yaml> would be the generated build spec saved from Step 1.
- For `docker` images downloaded from Dockerhub, you could also use <docker-image-name> as the argument.
- Run `docker images` to check list of available images on your machine.
```
$ llama stack configure 8b-instruct
$ llama stack configure tgi
Configuring API: inference (meta-reference)
Enter value for model (existing: Meta-Llama3.1-8B-Instruct) (required):
@ -332,10 +331,10 @@ Enter value for wolfram_api_key (optional):
Configuring API: telemetry (console)
YAML configuration has been written to ~/.llama/builds/conda/8b-instruct-run.yaml
YAML configuration has been written to ~/.llama/builds/conda/tgi-run.yaml
```
After this step is successful, you should be able to find a run configuration spec in `~/.llama/builds/conda/8b-instruct-run.yaml` with the following contents. You may edit this file to change the settings.
After this step is successful, you should be able to find a run configuration spec in `~/.llama/builds/conda/tgi-run.yaml` with the following contents. You may edit this file to change the settings.
As you can see, we did basic configuration above and configured:
- inference to run on model `Meta-Llama3.1-8B-Instruct` (obtained from `llama model list`)
@ -351,13 +350,13 @@ Note that all configurations as well as models are stored in `~/.llama`
Now, let's start the Llama Stack Distribution Server. You will need the YAML configuration file which was written out at the end by the `llama stack configure` step.
```
llama stack run 8b-instruct
llama stack run tgi
```
You should see the Llama Stack server start and print the APIs that it is supporting
```
$ llama stack run 8b-instruct
$ llama stack run tgi
> initializing model parallel with size 1
> initializing ddp with size 1

48
llama_stack/cli/stack/build.py
View file

@ -62,17 +62,12 @@ class StackBuild(Subcommand):
help="Show the available templates for building a Llama Stack distribution",
)
self.parser.add_argument(
"--name",
type=str,
help="Name of the Llama Stack build to override from template config. This name will be used as paths to store configuration files, build conda environments/docker images. If not specified, will use the name from the template config. ",
)
self.parser.add_argument(
"--image-type",
type=str,
help="Image Type to use for the build. This can be either conda or docker. If not specified, will use the image type from the template config.",
choices=["conda", "docker"],
default="conda",
)
def _run_stack_build_command(self, args: argparse.Namespace) -> None:
@ -91,15 +86,9 @@ class StackBuild(Subcommand):
return
if args.template:
if not args.name:
self.parser.error(
"You must specify a name for the build using --name when using a template"
)
return
available_templates = available_templates_specs()
for build_config in available_templates:
if build_config.name == args.template:
build_config.name = args.name
if args.image_type:
build_config.image_type = args.image_type
else:
@ -114,21 +103,7 @@ class StackBuild(Subcommand):
)
return
# try to see if we can find a pre-existing build config file through name
if args.name:
maybe_build_config = self._get_build_config_from_name(args)
if maybe_build_config:
cprint(
f"Building from existing build config for {args.name} in {str(maybe_build_config)}...",
"green",
)
with open(maybe_build_config, "r") as f:
build_config = BuildConfig(**yaml.safe_load(f))
self._run_stack_build_command_from_build_config(build_config)
return
if not args.config and not args.template:
if not args.name:
name = prompt(
"> Enter a name for your Llama Stack (e.g. my-local-stack): ",
validator=Validator.from_callable(
@ -136,8 +111,6 @@ class StackBuild(Subcommand):
error_message="Name cannot be empty, please enter a name",
),
)
else:
name = args.name
image_type = prompt(
"> Enter the image type you want your Llama Stack to be built as (docker or conda): ",
@ -203,25 +176,6 @@ class StackBuild(Subcommand):
return
self._run_stack_build_command_from_build_config(build_config)
def _get_build_config_from_name(self, args: argparse.Namespace) -> Optional[Path]:
if os.getenv("CONDA_PREFIX", ""):
conda_dir = (
Path(os.getenv("CONDA_PREFIX")).parent / f"llamastack-{args.name}"
)
else:
cprint(
"Cannot find CONDA_PREFIX. Trying default conda path ~/.conda/envs...",
color="green",
)
conda_dir = (
Path(os.path.expanduser("~/.conda/envs")) / f"llamastack-{args.name}"
)
build_config_file = Path(conda_dir) / f"{args.name}-build.yaml"
if build_config_file.exists():
return build_config_file
return None
def _run_stack_build_command_from_build_config(
self, build_config: BuildConfig
) -> None:

19
llama_stack/cli/stack/configure.py
View file

@ -55,19 +55,12 @@ class StackConfigure(Subcommand):
docker_image = None
build_config_file = Path(args.config)
if build_config_file.exists():
with open(build_config_file, "r") as f:
build_config = BuildConfig(**yaml.safe_load(f))
self._configure_llama_distribution(build_config, args.output_dir)
return
# if we get here, we need to try to find the conda build config file
cprint(
f"Could not find {build_config_file}. Trying conda build name instead...",
color="green",
)
conda_dir = (
Path(os.path.expanduser("~/.conda/envs")) / f"llamastack-{args.config}"
)
@ -80,19 +73,14 @@ class StackConfigure(Subcommand):
break
build_config_file = Path(conda_dir) / f"{args.config}-build.yaml"
if build_config_file.exists():
with open(build_config_file, "r") as f:
build_config = BuildConfig(**yaml.safe_load(f))
cprint(f"Using {build_config_file}...", "green")
self._configure_llama_distribution(build_config, args.output_dir)
return
# if we get here, we need to try to find the docker image
cprint(
f"Could not find {build_config_file}. Trying docker image name instead...",
color="green",
)
docker_image = args.config
builds_dir = BUILDS_BASE_DIR / ImageType.docker.value
if args.output_dir:
@ -105,15 +93,10 @@ class StackConfigure(Subcommand):
script_args = [script, docker_image, str(builds_dir)]
return_code = run_with_pty(script_args)
# we have regenerated the build config file with script, now check if it exists
if return_code != 0:
self.parser.error(
f"Failed to configure container {docker_image} with return code {return_code}. Please run `llama stack build` first. "
)
return
return
def _configure_llama_distribution(
self,

7
llama_stack/distribution/configure.py
View file

@ -99,6 +99,13 @@ def configure_api_providers(
cprint(f"Configuring API `{api_str}`...", "green", attrs=["bold"])
updated_providers = []
for i, provider_type in enumerate(plist):
if i >= 1:
others = ", ".join(plist[i:])
print(
f"Not configuring other providers ({others}) interactively. Please edit the resulting YAML directly.\n"
)
break
print(f"> Configuring provider `({provider_type})`")
updated_providers.append(
configure_single_provider(