mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-05 20:27:35 +00:00
feat: add embedding and dynamic model support to Together inference adapter
- updated to use OpenAIMixin - workarounds for Together api quirks - recordings for together suite when subdirs=inference,pattern=openai test with: `TOGETHER_API_KEY=_NONE_ ./scripts/integration-tests.sh --stack-config server:ci-tests --setup together --subdirs inference --pattern openai`
This commit is contained in:
parent
f4ab154ade
commit
3e02dc5c2f
20 changed files with 9227 additions and 180 deletions
|
@ -100,6 +100,14 @@ SETUP_DEFINITIONS: dict[str, Setup] = {
|
|||
"text_model": "tgi/Qwen/Qwen3-0.6B",
|
||||
},
|
||||
),
|
||||
"together": Setup(
|
||||
name="together",
|
||||
description="Together computer models",
|
||||
defaults={
|
||||
"text_model": "together/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free",
|
||||
"embedding_model": "together/togethercomputer/m2-bert-80M-32k-retrieval",
|
||||
},
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue