phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-07-21 20:18:52 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

distro readmes with model serving instructions (#339)

Browse source 
* readme updates

* quantied compose

* dell tgi

* config update

* readme

* update model serving readmes

* update

* update

* config
This commit is contained in:
Xi Yan 2024-10-28 17:47:14 -07:00 • committed by GitHub
parent a70a4706fc
commit ae671eaf7a
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
8 changed files with 136 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

23
distributions/together/README.md
View file

@ -56,3 +56,26 @@ llama stack build --template together --image-type conda
# -- modify run.yaml to a valid Together server endpoint
llama stack run ./run.yaml
```
### Model Serving
Use `llama-stack-client models list` to check the available models served by together.
```
$ llama-stack-client models list
+------------------------------+------------------------------+---------------+------------+
| identifier | llama_model | provider_id | metadata |
+==============================+==============================+===============+============+
| Llama3.1-8B-Instruct | Llama3.1-8B-Instruct | together0 | {} |
+------------------------------+------------------------------+---------------+------------+
| Llama3.1-70B-Instruct | Llama3.1-70B-Instruct | together0 | {} |
+------------------------------+------------------------------+---------------+------------+
| Llama3.1-405B-Instruct | Llama3.1-405B-Instruct | together0 | {} |
+------------------------------+------------------------------+---------------+------------+
| Llama3.2-3B-Instruct | Llama3.2-3B-Instruct | together0 | {} |
+------------------------------+------------------------------+---------------+------------+
| Llama3.2-11B-Vision-Instruct | Llama3.2-11B-Vision-Instruct | together0 | {} |
+------------------------------+------------------------------+---------------+------------+
| Llama3.2-90B-Vision-Instruct | Llama3.2-90B-Vision-Instruct | together0 | {} |
+------------------------------+------------------------------+---------------+------------+
```

13
distributions/together/run.yaml
View file

@ -17,11 +17,18 @@ providers:
provider_type: remote::together
config:
url: https://api.together.xyz/v1
# api_key: <ENTER_YOUR_API_KEY>
safety:
- provider_id: together0
provider_type: remote::together
- provider_id: meta0
provider_type: meta-reference
config:
url: https://api.together.xyz/v1
llama_guard_shield:
model: Llama-Guard-3-1B
excluded_categories: []
disable_input_check: false
disable_output_check: false
prompt_guard_shield:
model: Prompt-Guard-86M
memory:
- provider_id: meta0
provider_type: remote::weaviate